#i73173# integrate Google SoC language-guessing

author: Thomas Lange <tl@openoffice.org> 2007-01-12 11:57:30 +0000
committer: Thomas Lange <tl@openoffice.org> 2007-01-12 11:57:30 +0000
commit: 0b876445efbd93c73879c216d564c0508cea530f (patch)
tree: 651fb2e3093ff5e3d5ad4afb9ba20435e42ed862 /libtextcat
parent: 23147b5b1f280e1c7758c4ce27b99dc92135b354 (diff)
65 files changed, 25204 insertions, 0 deletions
diff --git a/libtextcat/data/new_fingerprints/lm/basque.lm b/libtextcat/data/new_fingerprints/lm/basque.lm
new file mode 100644
index 000000000000..32522a7eca20
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/basque.lm
@@ -0,0 +1,400 @@
+_	 12114
+a	 5537
+e	 4040
+i	 3103
+t	 2567
+n	 2474
+r	 2406
+o	 1937
+k	 1761
+z	 1627
+u	 1561
+d	 1367
+l	 1075
+s	 1048
+b	 995
+n_	 958
+a_	 957
+en	 802
+g	 772
+_e	 736
+er	 680
+ra	 669
+.	 625
+at	 610
+_b	 594
+ar	 589
+an	 585
+_d	 580
+,	 569
+,_	 569
+h	 563
+ta	 563
+te	 555
+._	 520
+ko	 513
+m	 503
+o_	 486
+al	 481
+en_	 471
+tz	 458
+re	 435
+_a	 423
+ik	 416
+in	 409
+it	 392
+za	 391
+ak	 388
+ba	 358
+et	 357
+da	 352
+di	 351
+ka	 350
+ze	 349
+ai	 347
+p	 340
+ri	 335
+la	 329
+an_	 327
+de	 322
+ez	 318
+na	 314
+ti	 307
+be	 305
+i_	 302
+iz	 294
+k_	 293
+tu	 289
+eta	 287
+(	 280
+)	 280
+_i	 279
+or	 276
+_(	 270
+ko_	 269
+ek	 265
+rr	 264
+_h	 263
+e_	 260
+es	 260
+_ba	 258
+nt	 258
+ha	 255
+_g	 247
+era	 246
+ia	 240
+_be	 234
+oa	 229
+un	 229
+ta_	 218
+ma	 212
+on	 211
+z_	 209
+du	 207
+(_	 205
+_(_	 205
+:	 204
+tze	 204
+:_	 204
+us	 191
+u_	 191
+_da	 188
+ren	 183
+az	 183
+_)	 183
+ur	 182
+st	 182
+ea	 181
+_et	 181
+eta_	 179
+zi	 178
+si	 177
+zen	 177
+as	 176
+_n	 175
+go	 175
+_eta	 172
+il	 169
+tik	 169
+_z	 167
+_eta_	 167
+ne	 167
+bi	 166
+zk	 166
+sk	 165
+ag	 163
+t_	 162
+le	 160
+rt	 160
+ke	 158
+-	 150
+gu	 148
+au	 148
+tza	 147
+_de	 147
+ati	 146
+ut	 146
+A	 145
+li	 145
+hi	 145
+E	 144
+bat	 144
+_o	 143
+a,	 142
+a,_	 142
+_m	 141
+ntz	 141
+ad	 140
+ren_	 139
+_er	 138
+io	 138
+)_	 138
+_ez	 138
+ir	 137
+eh	 137
+ab	 135
+ate	 135
+ak_	 134
+sa	 134
+ra_	 134
+_bat	 133
+nd	 133
+_l	 133
+ki	 132
+ere	 131
+ika	 125
+ku	 125
+f	 124
+ga	 123
+ld	 122
+_di	 121
+arr	 120
+el	 120
+eg	 119
+uz	 119
+are	 116
+ng	 116
+os	 116
+_E	 115
+gi	 113
+_p	 113
+_du	 113
+mo	 113
+zen_	 112
+ib	 111
+_k	 110
+ber	 109
+ako	 108
+_iz	 107
+iza	 107
+ala	 107
+itz	 107
+har	 106
+eko	 106
+adi	 105
+l_	 105
+ie	 105
+ste	 105
+atu	 104
+am	 104
+ska	 104
+ah	 104
+_.	 104
+r_	 104
+zt	 103
+rri	 103
+ait	 103
+ua	 103
+tzen	 103
+ald	 103
+usk	 102
+aren	 102
+_._	 102
+ro	 102
+id	 100
+la_	 99
+_s	 98
+ue	 98
+tek	 97
+uska	 97
+atz	 96
+aren_	 96
+_ha	 95
+rre	 95
+"	 94
+atik	 94
+tzen_	 94
+ara	 94
+in_	 93
+ni	 93
+j	 92
+ge	 91
+ez_	 91
+ain	 91
+od	 91
+no	 91
+na_	 91
+ri_	 90
+tan	 90
+mat	 90
+do	 89
+_mo	 88
+ho	 88
+iko	 88
+beh	 88
+_ad	 88
+al_	 87
+_iza	 87
+I	 87
+zan	 87
+_ze	 87
+_adi	 87
+_A	 86
+uk	 86
+eha	 85
+dit	 85
+ru	 85
+pe	 85
+eko_	 84
+ela	 84
+ed	 84
+kar	 84
+n,_	 83
+ari	 83
+bil	 83
+_beh	 83
+bai	 83
+tu_	 83
+n,	 83
+ehar	 83
+_izan	 82
+itu	 82
+_ho	 82
+is	 82
+ean	 82
+ama	 82
+izan	 82
+_)_	 81
+ik_	 81
+B	 80
+koa	 80
+ot	 80
+_na	 79
+zu	 79
+beha	 78
+behar	 78
+_t	 78
+H	 78
+_ko	 78
+dir	 77
+mati	 76
+_j	 75
+at_	 75
+em	 74
+tika	 74
+K	 74
+_B	 74
+zte	 74
+ten	 74
+_beha	 74
+ter	 74
+matik	 73
+egi	 73
+_dir	 73
+a.	 72
+ago	 72
+kal	 72
+ram	 72
+ena	 72
+unt	 71
+lt	 71
+_H	 71
+su	 71
+mod	 71
+bo	 71
+G	 70
+_ber	 70
+lde	 70
+c	 69
+te_	 69
+ar_	 69
+me	 69
+ina	 69
+dal	 69
+ako_	 68
+L	 68
+rik	 68
+a._	 68
+ori	 68
+ite	 68
+raz	 67
+alde	 67
+)._	 67
+).	 67
+zio	 66
+_ez_	 66
+tan_	 66
+amat	 66
+atika	 66
+est	 66
+ntza	 65
+dut	 65
+izk	 65
+_ga	 65
+ia_	 65
+s_	 65
+ita	 65
+tea	 64
+ei	 64
+hal	 64
+_mod	 64
+pa	 64
+bu	 64
+re_	 63
+eu	 63
+ert	 63
+oa_	 63
+_era	 63
+ten_	 63
+_G	 63
+_eg	 63
+rama	 63
+odal	 63
+ramat	 63
+oda	 63
+amati	 62
+atze	 62
+gr	 62
+untz	 62
+eza	 62
+gra	 62
+_ge	 61
+gram	 61
+kat	 61
+abi	 61
+_gr	 60
+_gram	 60
+_gra	 60
+int	 60
+rd	 60
+_in	 60
+k,	 59
+_hi	 59
+zko	 59
+k,_	 59
+pr	 59
+rab	 59
+da_	 59
+ide	 58
+_)._	 57
+tat	 57
+ing	 57
+ira	 57
+tak	 57
+x	 57
+_).	 57
+_ed	 57
+_es	 57
+_bi	 57
+rak	 56
+_-	 56
diff --git a/libtextcat/data/new_fingerprints/lm/belarus.lm b/libtextcat/data/new_fingerprints/lm/belarus.lm
new file mode 100644
index 000000000000..7d58602e51c3
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/belarus.lm
@@ -0,0 +1,400 @@
+_
+а
+н
+р
+е
+i
+к
+ы
+л
+у
+я
+с
+т
+д
+а_
+о
+м
+в
+ц
+з
+.
+на
+г
+п
+ка
+._
+ра
+ч
+i_
+э
+ал
+у_
+ар
+ан
+я_
+та
+,
+б
+,_
+ва
+ы_
+ш
+_с
+ла
+ь
+й
+_д
+ле
+га
+_а
+ад
+_п
+ры
+да
+_у
+ен
+ты
+й_
+е_
+_г
+ны
+_н
+на_
+зе
+_в
+-
+_б
+ас
+ам
+_i
+ав
+ро
+аг
+_у_
+_з
+па
+нн
+ск
+х
+ю
+_м
+не
+дз
+_i_
+_к
+А
+ыя
+пр
+ст
+ак
+ын
+iк
+ль
+ня
+нi
+лi
+за
+аз
+ру
+ет
+ж
+ян
+ку
+ля
+ай
+_М
+_А
+_я
+нс
+ага
+ат
+ай_
+М
+але
+га_
+ага_
+ме
+_на
+ала
+"
+_па
+тр
+ер
+кал
+кi
+м_
+кт
+ава
+вi
+дзе
+нск
+ана
+В
+го
+ац
+сц
+а.
+)
+о_
+iн
+_ад
+цы
+ца
+а._
+тар
+ма
+цi
+ау
+ь_
+ска
+ча
+_ка
+са
+р_
+_._
+як
+_га
+_р
+_т
+_пр
+_за
+ве
+ся
+ны_
+да_
+др
+мi
+бы
+_.
+рэ
+ара
+он
+оу
+_да
+ек
+и
+лек
+_У
+ым
+ыл
+ая
+ло
+нк
+нт
+пра
+)_
+пi
+ары
+_на_
+та_
+рн
+х_
+У
+сi
+шы
+кр
+ая_
+ел
+ван
+ец
+ста
+чы
+_бы
+ае
+I
+_э
+_П
+iка
+яу
+эд
+(
+iм
+газе
+_газ
+_газе
+_I
+азе
+_)
+вя
+_(
+iч
+тро
+ня_
+аш
+ор
+газ
+_)_
+ов
+аван
+П
+ран
+ун
+ля_
+ар_
+дак
+вар
+_да_
+ыян
+св
+черн
+_Я
+ык
+ктрон
+трон
+эл
+'
+ект
+ектро
+но
+нага_
+нна
+--
+iл
+ку_
+няу
+-_
+Ал
+Ве
+был
+рыя
+онн
+_-
+ронн
+iя
+эдак
+ктр
+кта
+сан
+лi_
+_"
+д_
+элект
+ап
+ктро
+_эл
+чер
+элек
+зе_
+лектр
+мп
+ерн
+_эле
+_кал
+нска
+ктар
+сцi
+Вечер
+ечер
+ач
+ечерн
+Я
+ам_
+ектр
+Вече
+кс
+_--_
+дзе_
+тронн
+наг
+Н
+эда
+Веч
+Б
+ты_
+зет
+ече
+лект
+_Ал
+еч
+ук
+ада
+рон
+_ва
+ла_
+_элек
+_был
+ус
+--_
+нага
+че
+вары
+эле
+_--
+рав
+уку
+каг
+_ш
+кай
+ний_
+На
+ий_
+ка.
+_ч
+ннаг
+ыц
+_Р
+рус
+_В
+_Н
+яр
+эн
+эм
+_Б
+кра
+черни
+у,_
+нд
+ни
+дакт
+лару
+нц
+кага_
+_Мин
+ныя
+Минс
+нь
+акта
+лар
+_для
+..
+_вар
+нiк
+i,
+_пра
+i.
+янт
+яна
+о,
+су
+(_
+бо
+ння
+ць
+рни
+цц
+це
+янта_
+дл
+_Минс
+ларус
+янта
+_го
+тэ
+к_
+_рэ
+ерни
+вы
+цца
+ана_
+ронна
+не_
+ндр
+зеты_
+_як
+Мин
+для_
+_для_
+елар
+Бел
+рыян
diff --git a/libtextcat/data/new_fingerprints/lm/bosnian.lm b/libtextcat/data/new_fingerprints/lm/bosnian.lm
new file mode 100644
index 000000000000..cf6b8a41ce67
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/bosnian.lm
@@ -0,0 +1,400 @@
+_	 9464
+a	 2787
+i	 2108
+e	 2077
+o	 2018
+j	 1396
+n	 1328
+s	 1170
+u	 1010
+r	 988
+d	 957
+a_	 889
+e_	 833
+t	 774
+je	 771
+k	 756
+l	 743
+m	 702
+v	 685
+p	 604
+c	 538
+i_	 538
+_s	 522
+u_	 476
+z	 463
+_p	 450
+o_	 433
+,_	 381
+,	 381
+_i	 369
+_n	 358
+b	 349
+_d	 349
+.	 346
+na	 341
+je_	 337
+._	 321
+_j	 307
+g	 299
+ra	 292
+st	 283
+ko	 278
+_je	 274
+ij	 254
+_o	 245
+ni	 240
+_k	 236
+an	 228
+oj	 227
+da	 226
+_u	 222
+pr	 221
+no	 219
+ma	 219
+la	 211
+ri	 206
+_je_	 203
+po	 203
+ci	 196
+_pr	 191
+os	 190
+od	 187
+ka	 186
+im	 185
+ti	 184
+li	 182
+vo	 178
+_po	 174
+ja	 171
+_i_	 169
+ov	 169
+al	 168
+re	 167
+ne	 167
+m_	 164
+ta	 160
+na_	 158
+ed	 157
+_m	 157
+_na	 157
+se	 156
+_u_	 154
+en	 153
+ic	 151
+sa	 151
+_b	 149
+ak	 141
+va	 140
+ad	 137
+h	 136
+ju	 135
+su	 134
+dj	 133
+ije	 133
+ar	 127
+ca	 127
+_z	 126
+nj	 125
+ji	 124
+da_	 124
+_ko	 123
+_da	 122
+il	 121
+"	 120
+av	 120
+_t	 118
+aj	 116
+ob	 115
+ro	 114
+am	 114
+vi	 114
+_su	 113
+om	 112
+dje	 112
+za	 112
+at	 111
+le	 111
+di	 110
+su_	 107
+iz	 107
+ve	 107
+lj	 106
+_se	 105
+ev	 105
+is	 105
+es	 103
+se_	 103
+do	 101
+ih	 100
+a,	 99
+_su_	 99
+a,_	 99
+on	 98
+bi	 98
+in	 97
+voj	 97
+az	 96
+ac	 95
+_da_	 95
+la_	 95
+_r	 93
+_g	 93
+jev	 92
+ma_	 92
+er	 92
+or	 91
+h_	 90
+_sa	 90
+e,	 90
+e,_	 90
+ba	 90
+ima	 89
+a.	 88
+ol	 88
+_do	 87
+dn	 87
+it	 87
+ko_	 86
+ne_	 86
+ost	 85
+ek	 85
+to	 85
+d_	 84
+as	 84
+ju_	 84
+ao	 84
+ih_	 84
+a._	 84
+te	 83
+evo	 83
+koj	 83
+pri	 82
+jevo	 82
+ce	 81
+_se_	 81
+og	 80
+go	 80
+jevoj	 79
+de	 79
+uc	 79
+evoj	 79
+_od	 78
+_za	 78
+tr	 78
+S	 77
+_koj	 76
+ke	 75
+_v	 75
+ao_	 75
+_dje	 74
+_bi	 74
+sta	 74
+_dj	 74
+cij	 74
+ik	 74
+djev	 73
+sl	 73
+_djev	 72
+ga	 72
+djevo	 72
+_ka	 71
+rij	 71
+_iz	 71
+P	 71
+_pri	 70
+_a	 69
+us	 68
+_S	 68
+mo	 67
+el	 67
+sk	 66
+me	 66
+zi	 66
+ija	 65
+n_	 65
+ku	 64
+im_	 63
+_st	 63
+ica	 63
+_na_	 62
+_ne	 62
+em	 61
+edn	 61
+jk	 61
+io	 61
+li_	 60
+ojk	 60
+evojk	 60
+_"	 60
+zn	 60
+vojk	 60
+pro	 59
+lo	 59
+ije_	 59
+jed	 58
+ke_	 58
+om_	 58
+jen	 58
+sti	 57
+_im	 57
+le_	 57
+_ra	 56
+e.	 56
+ze	 55
+_pro	 55
+nu	 55
+nje	 55
+ti_	 55
+ec	 55
+pre	 55
+oc	 54
+aci	 54
+no_	 54
+et	 54
+oji	 53
+si	 53
+ara	 53
+ama	 53
+z_	 53
+pos	 52
+rad	 52
+ran	 52
+ima_	 52
+ru	 52
+_P	 52
+tu	 52
+mu	 51
+e._	 51
+ja_	 50
+_pre	 50
+sa_	 49
+io_	 49
+od_	 48
+ni_	 48
+_nj	 48
+j_	 48
+_pos	 47
+_c	 47
+ila	 47
+K	 46
+_sa_	 46
+uz	 46
+N	 46
+_ni	 45
+zna	 45
+U	 45
+za_	 45
+_no	 45
+ako	 45
+u,	 44
+lu	 44
+ali	 44
+u,_	 44
+sto	 44
+ste	 44
+ve_	 44
+ani	 44
+oli	 44
+aka	 44
+_jed	 43
+i,_	 43
+ji_	 43
+uci	 43
+i,	 43
+ci_	 43
+osti	 43
+_N	 42
+dr	 42
+so	 42
+ust	 41
+ila_	 41
+B	 41
+-	 41
+red	 41
+jke	 41
+sv	 41
+_go	 41
+bar	 41
+g_	 41
+est	 40
+D	 40
+iv	 40
+vojke	 40
+aju	 40
+ta_	 40
+A	 40
+lje	 40
+jedn	 40
+bil	 40
+ojke	 40
+ova	 40
+ati	 39
+_mu	 39
+pa	 39
+M	 39
+_ba	 39
+ca_	 39
+O	 39
+ka_	 39
+_a_	 38
+_B	 38
+_ima	 38
+sn	 38
+nu_	 38
+T	 38
+to_	 38
+eg	 38
+ava	 38
+ros	 37
+ir	 37
+ala	 37
+og_	 37
+osl	 37
+ovi	 37
+koji	 37
+_sv	 37
+dv	 36
+ric	 36
+_za_	 36
+br	 36
+_on	 36
+odi	 36
+_koji	 36
+_jedn	 35
+nik	 35
+dno	 35
+_D	 35
+jo	 35
+tra	 35
+_M	 35
+sp	 35
+iz_	 35
+oz	 35
+vr	 35
+u.	 35
+eri	 35
+I	 35
+eko	 35
+ale	 35
+_ma	 34
+lik	 34
+_bil	 34
+c_	 34
+ut	 34
+je,_	 34
+u._	 34
+str	 34
+je,	 34
+adi	 34
+tit	 34
+_iz_	 34
+iti	 34
+i.	 33
+_rad	 33
+ici	 33
+rost	 33
+aju_	 33
+va_	 33
+_ob	 33
+nog	 33
diff --git a/libtextcat/data/new_fingerprints/lm/breton.lm b/libtextcat/data/new_fingerprints/lm/breton.lm
new file mode 100644
index 000000000000..6d021d739672
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/breton.lm
@@ -0,0 +1,400 @@
+_	 21447
+e	 6375
+a	 5414
+n	 3228
+r	 3039
+o	 2968
+t	 2392
+i	 1812
+h	 1751
+u	 1650
+l	 1630
+d	 1506
+a_	 1352
+z	 1319
+t_	 1310
+_e	 1168
+_a	 1168
+e_	 1133
+m	 1105
+s	 1100
+g	 1090
+r_	 998
+k	 997
+n_	 958
+et	 941
+v	 888
+_d	 868
+an	 859
+.	 846
+'	 841
+en	 836
+b	 757
+,	 749
+,_	 743
+._	 716
+ar	 703
+ou	 700
+et_	 689
+c	 686
+ez	 572
+'h	 572
+_g	 565
+er	 555
+p	 553
+_k	 535
+c'h	 530
+c'	 530
+nt	 513
+_h	 505
+re	 505
+ra	 478
+ha	 466
+ñ	 458
+ne	 456
+oa	 454
+_o	 442
+_b	 434
+-	 432
+zh	 422
+ar_	 415
+_m	 414
+_e_	 414
+nn	 384
+el	 376
+_a_	 356
+ur	 350
+o_	 346
+h_	 345
+ve	 340
+nt_	 340
+w	 339
+ke	 338
+de	 333
+añ	 332
+_p	 332
+s_	 327
+he	 325
+on	 318
+le	 318
+ga	 316
+ma	 315
+_ar	 312
+eu	 312
+_n	 310
+an_	 298
+ant	 296
+enn	 285
+z_	 282
+_ar_	 281
+be	 280
+_v	 276
+_r	 272
+al	 270
+en_	 268
+_ke	 267
+l_	 264
+em	 264
+_c	 263
+ñ_	 262
+da	 262
+_s	 261
+ho	 260
+di	 259
+_ha	 252
+ll	 250
+tr	 248
+oa_	 247
+me	 246
+us	 242
+_ga	 234
+la	 231
+ket	 227
+ant_	 219
+_da	 219
+_l	 216
+ur_	 216
+_oa	 215
+in	 214
+ket_	 211
+gan	 211
+_c'	 207
+_u	 207
+_c'h	 207
+ad	 207
+añ_	 207
+ao	 204
+_ma	 204
+_t	 204
+_ket	 201
+_an	 199
+_di	 197
+ezh	 196
+ù	 196
+où	 196
+_de	 195
+ev	 193
+?	 192
+st	 192
+ro	 192
+P	 192
+_ket_	 188
+er_	 188
+f	 186
+na	 186
+ue	 185
+da_	 184
+?_	 184
+_gan	 184
+_da_	 184
+_ne	 183
+ed	 182
+_P	 180
+g_	 180
+pe	 179
+m_	 178
+A	 177
+ri	 176
+us_	 175
+ta	 174
+ze	 174
+gant	 174
+ka	 174
+i_	 172
+d_	 171
+G	 167
+te	 167
+ae	 166
+zh_	 164
+ha_	 163
+_ha_	 163
+_he	 161
+_gant	 159
+do	 159
+oue	 159
+_G	 158
+eus	 158
+eo	 158
+'h_	 157
+_en	 157
+go	 157
+am	 157
+c'h_	 157
+_be	 156
+we	 156
+iz	 154
+_an_	 151
+_A	 150
+eus_	 147
+sk	 147
+li	 146
+as	 146
+_pe	 146
+j	 146
+_oa_	 146
+av	 144
+gant_	 143
+ut	 142
+no	 141
+vez	 140
+va	 140
+_ra	 140
+ge	 138
+ez_	 138
+bo	 137
+ 	 137
+_ur	 136
+lo	 134
+he_	 134
+où_	 133
+ù_	 133
+_ur_	 132
+es	 130
+'ho	 129
+ni	 129
+uz	 129
+tra	 127
+se	 126
+it	 125
+ra_	 125
+out	 125
+is	 125
+at	 125
+hi	 125
+eg	 125
+ig	 124
+ko	 124
+io	 123
+k_	 123
+ch	 123
+_w	 121
+or	 121
+Pe	 121
+_ma_	 119
+ma_	 119
+gw	 118
+_em	 118
+_Pe	 118
+un	 118
+eme	 117
+ne_	 117
+nn_	 117
+c'ho	 117
+ol	 116
+ag	 116
+M	 115
+'ha	 115
+_en_	 115
+iv	 115
+vi	 113
+_ka	 113
+K	 113
+ud	 112
+_he_	 111
+ont	 110
+oc	 110
+vo	 110
+ec	 109
+wa	 109
+..	 107
+_M	 107
+_z	 107
+br	 107
+om	 106
+to	 105
+_f	 105
+N	 105
+_c'ho	 104
+ti	 104
+ut_	 104
+D	 104
+_o_	 103
+_la	 103
+_go	 101
+az	 101
+out_	 101
+ba	 101
+enn_	 101
+c'ha	 101
+our	 100
+oc'h	 100
+ell	 100
+oc'	 100
+etr	 99
+el_	 99
+_K	 99
+_D	 99
+:	 99
+:_	 99
+eve	 98
+_d'	 97
+all	 97
+d'	 97
+E	 97
+_ne_	 97
+_me	 95
+eo_	 95
+ak	 95
+bet	 95
+_eu	 95
+rc	 94
+_do	 94
+_gw	 94
+zi	 93
+oz	 93
+aou	 93
+etra	 92
+pa	 91
+ab	 90
+on_	 90
+ei	 90
+tra_	 90
+n,	 89
+zo	 89
+ag_	 89
+_ev	 88
+ul	 88
+'e	 88
+n'	 88
+n,_	 88
+ouz	 87
+v_	 86
+_n'	 86
+_eus	 84
+H	 83
+za	 83
+S	 83
+etra_	 83
+_eo	 82
+t,_	 82
+t,	 82
+il	 81
+ent	 81
+fe	 81
+rc'h	 81
+rc'	 81
+_eus_	 80
+ie	 80
+_bo	 79
+ele	 79
+_ve	 79
+mp	 79
+_bet	 78
+B	 78
+it_	 77
+_vo	 77
+'a	 77
+n.	 76
+_S	 76
+hag	 76
+hoa	 75
+_hag	 75
+len	 75
+_N	 75
+'hoa	 74
+_E	 74
+ir	 74
+hag_	 74
+_hag_	 74
+mañ	 74
+as_	 73
+eze	 73
+ont_	 73
+_.	 73
+iñ	 73
+r,	 72
+pr	 72
+ed_	 72
+n._	 72
+re_	 72
+in_	 72
+r,_	 72
+_H	 71
+'he	 70
+t.	 70
+gou	 70
+em_	 70
+_br	 70
+rae	 70
+rez	 69
+t._	 69
+bet_	 69
+net	 69
+dr	 68
+_eo_	 68
+ll_	 68
+mo	 67
+po	 67
+oul	 67
+rou	 67
+c'hoa	 67
+a-	 67
+vel	 67
+oc'h_	 67
+nna	 66
+_B	 66
+met	 65
+ec'	 65
+ec'h	 65
+R	 64
+den	 64
diff --git a/libtextcat/data/new_fingerprints/lm/catalan.lm b/libtextcat/data/new_fingerprints/lm/catalan.lm
new file mode 100644
index 000000000000..086a45b50c50
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/catalan.lm
@@ -0,0 +1,400 @@
+_	 16604
+e	 5091
+a	 4937
+s	 3120
+r	 3037
+i	 2987
+l	 2747
+n	 2641
+t	 2466
+o	 2274
+d	 1775
+c	 1740
+u	 1515
+a_	 1460
+s_	 1416
+_d	 1116
+e_	 1067
+p	 1014
+m	 995
+es	 985
+de	 972
+_de	 842
+en	 700
+_l	 691
+re	 652
+_e	 637
+de_	 611
+el	 602
+_de_	 601
+_a	 600
+,	 599
+,_	 599
+er	 598
+la	 584
+ar	 583
+_p	 550
+l_	 547
+ci	 522
+n_	 518
+es_	 515
+an	 515
+ra	 499
+nt	 495
+ta	 495
+b	 476
+_c	 452
+al	 450
+v	 440
+g	 428
+.	 420
+on	 420
+or	 404
+t_	 402
+at	 396
+._	 377
+r_	 372
+i_	 371
+la_	 368
+_i	 364
+_la	 351
+_la_	 325
+f	 325
+le	 322
+te	 312
+'	 311
+_s	 308
+st	 308
+se	 305
+ó	 302
+ue	 302
+na	 301
+os	 301
+qu	 300
+q	 300
+el_	 299
+it	 292
+co	 290
+ri	 277
+ca	 277
+ti	 273
+ac	 272
+in	 268
+ll	 264
+ic	 264
+me	 259
+un	 257
+que	 248
+C	 248
+tr	 244
+ns	 242
+ió	 238
+_i_	 236
+ad	 233
+ent	 232
+_el	 227
+ne	 226
+_t	 223
+_co	 221
+_m	 221
+_C	 217
+en_	 217
+li	 217
+ia	 212
+à	 212
+pe	 207
+_a_	 207
+pr	 206
+ció	 203
+ó_	 203
+pa	 203
+ro	 202
+o_	 198
+E	 198
+di	 197
+io	 197
+ls	 196
+h	 192
+_q	 192
+_qu	 192
+_en	 187
+aci	 186
+am	 186
+ec	 183
+to	 183
+as	 180
+om	 180
+ni	 180
+da	 179
+ió_	 179
+si	 178
+ls_	 176
+L	 175
+ma	 172
+res	 172
+ur	 171
+_el_	 162
+rt	 162
+ue_	 160
+A	 160
+os_	 159
+_que	 159
+que_	 158
+_r	 158
+po	 157
+_es	 155
+er_	 155
+_que_	 155
+M	 155
+_se	 153
+va	 153
+del	 153
+ció_	 151
+_pr	 151
+is	 150
+_en_	 149
+P	 147
+_pe	 146
+_del	 145
+ts	 145
+lo	 145
+_M	 144
+ct	 144
+_u	 144
+ol	 143
+ve	 141
+_L	 140
+x	 140
+y	 140
+a,_	 139
+a,	 139
+nc	 138
+men	 137
+al_	 137
+_f	 137
+_re	 137
+_P	 136
+ació	 136
+les	 136
+rs	 134
+est	 133
+tu	 131
+_E	 130
+et	 130
+s,_	 129
+_un	 129
+na_	 129
+_v	 129
+s,	 129
+ion	 127
+per	 126
+so	 125
+em	 125
+at_	 124
+no	 124
+j	 124
+br	 123
+nt_	 122
+ar_	 122
+sa	 121
+_n	 119
+les_	 118
+é	 118
+ce	 117
+il	 117
+ell	 116
+_per	 114
+í	 114
+ob	 113
+re_	 113
+ir	 113
+_A	 112
+ons	 112
+do	 112
+ua	 112
+con	 112
+ment	 111
+gu	 111
+ts_	 110
+ss	 110
+ns_	 109
+ant	 109
+ra_	 109
+Co	 109
+par	 108
+l'	 107
+d'	 107
+_l'	 107
+els	 107
+tat	 107
+sc	 106
+_d'	 106
+an_	 105
+_Co	 105
+vi	 104
+els_	 104
+ica	 104
+ran	 103
+ul	 102
+iv	 102
+S	 102
+_del_	 102
+del_	 102
+mb	 101
+mi	 101
+ita	 101
+nta	 100
+_pa	 99
+_o	 99
+_con	 98
+ació_	 97
+rn	 96
+_in	 96
+ia_	 96
+z	 96
+im	 95
+rr	 95
+art	 94
+ta_	 93
+com	 93
+tre	 92
+_h	 92
+s.	 91
+mp	 90
+ie	 90
+J	 90
+s._	 89
+cio	 89
+_le	 89
+bre	 88
+_ca	 88
+_al	 88
+sta	 88
+_com	 88
+cu	 88
+à_	 87
+pre	 87
+fe	 86
+ba	 86
+tra	 86
+ge	 85
+pro	 85
+_les	 84
+des	 84
+ter	 84
+_po	 84
+_les_	 84
+T	 84
+_J	 84
+nd	 84
+cion	 84
+_S	 84
+ura	 83
+nci	 82
+va_	 81
+ha	 81
+ona	 81
+ent_	 80
+ues	 80
+oc	 80
+ea	 80
+nte	 80
+és	 80
+_di	 79
+ui	 79
+as_	 78
+ut	 78
+ici	 78
+res_	 78
+us	 77
+ot	 77
+ara	 77
+ip	 75
+rm	 75
+ab	 75
+eg	 75
+_per_	 75
+ng	 75
+'a	 75
+I	 75
+per_	 75
+rec	 74
+du	 74
+_tr	 74
+è	 73
+cia	 73
+_no	 73
+b_	 73
+_par	 72
+ep	 72
+id	 72
+lle	 71
+rc	 71
+_pro	 70
+D	 69
+G	 69
+ga	 69
+fo	 69
+una	 68
+El	 68
+lit	 68
+un_	 68
+ques	 68
+amb	 67
+ix	 67
+és_	 67
+_G	 67
+era	 67
+cr	 67
+)	 66
+da_	 66
+-	 66
+sp	 66
+y_	 66
+ada	 66
+tor	 66
+(	 66
+_(	 66
+_T	 65
+ment_	 65
+B	 65
+_es_	 65
+Ma	 65
+V	 65
+uc	 65
+ect	 65
+ame	 64
+iu	 64
+_Ma	 64
+orn	 64
+_B	 64
+_D	 64
+Ca	 64
+sti	 64
+_g	 63
+esc	 63
+rd	 63
+una_	 63
+là	 62
+"	 62
+ed	 62
+amen	 61
+mo	 61
+ions	 61
+_El	 61
+_Ca	 61
+Jo	 61
+eu	 61
+ari	 61
+lt	 61
+F	 61
+u_	 61
+ament	 60
+_V	 60
+m_	 60
+fi	 60
+au	 60
+ev	 60
+La	 60
+itat	 59
+_ha	 59
diff --git a/libtextcat/data/new_fingerprints/lm/chinese_simplified.lm b/libtextcat/data/new_fingerprints/lm/chinese_simplified.lm
new file mode 100644
index 000000000000..622b89c3ba80
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/chinese_simplified.lm
@@ -0,0 +1,400 @@
+_
+，_
+_，_
+_，
+，
+的
+的_
+_的
+_的_
+_。
+。_
+。
+_。_
+国
+了_
+了
+_了_
+在
+_了
+_￥_
+_在
+_１_
+_１
+_￥
+国_
+１
+在_
+￥_
+￥
+年
+１_
+_在_
+_０
+_０_
+部
+０
+０_
+５_
+民
+_５
+_５_
+５
+政
+工
+、_
+_年
+_日
+日
+_、
+年_
+行
+_、_
+建
+、
+４
+多_
+多
+６
+百
+作
+会
+日_
+_百
+_建
+理
+和
+_４
+军
+_多
+_多_
+_百_
+_部
+_日_
+关
+_６_
+和_
+成
+百_
+_６
+_和_
+_和
+４_
+进
+６_
+_军
+_４_
+_万_
+９
+我
+_万
+展
+得
+地
+们
+产
+举
+过
+主
+上
+目
+行_
+于
+一
+万
+_国
+全
+发
+到_
+_进
+_工
+_过
+人
+_９_
+_我
+到
+个_
+个
+_上
+_９
+万_
+_举
+不
+部_
+_关
+９_
+们_
+长
+_政
+开
+战
+经
+_性
+_上_
+并
+性
+治_
+大
+_工作
+_个
+民_
+_内_
+他
+这
+_内
+治
+计
+品
+术
+工作_
+共
+县
+内
+―_
+区_
+员_
+_―
+术_
+_工作_
+上_
+部门
+_部门
+作_
+_并
+_这
+一_
+于_
+分
+区
+品_
+_引
+_开
+系
+员
+县_
+_―_
+_不
+工作
+_一_
+―
+_发
+_到_
+_他
+_到
+_民
+主义
+_年_
+_全
+生
+_共
+_个_
+性_
+门
+_性_
+地_
+往
+机
+案
+引
+合
+内_
+_一
+展_
+义
+府
+问题_
+里_
+常
+取得了
+市
+期
+这_
+数
+门_
+就
+要_
+等_
+小
+他_
+字
+家
+社会
+技
+得_
+将
+_分_
+取得了_
+营
+８
+女
+级
+约
+_将_
+绝
+统
+厂_
+我们
+安
+字_
+_厂_
+大_
+＃_
+_作
+工_
+文
+将_
+新
+组
+外
+_已_
+已
+产_
+_中
+_产
+_技术_
+_生产
+过_
+但
+价
+绝_
+均
+坏
+已_
+_之
+_技
+家_
+事
+２
+_举行_
+联合国_
+中
+严
+训
+_元_
+_等_
+往_
+之
+_但
+_发展
+问题
+_机
+后
+_取得了_
+_市_
+政治_
+厂
+_战
+取
+务
+_但_
+十
+长_
+政_
+几
+刚
+_成
+_十_
+事_
+_会
+_８_
+会主义
+部门_
+_女
+_２_
+机_
+_已
+_”
+理_
+公
+各
+技术
+元_
+_职工
+经济_
+举行
+_＃_
+_军民
+_问题
+义_
+之_
+举行_
+_新
+解
+_两
+_这_
+得了
+_得_
+_几_
+_问
+两_
+我们_
+进行
+取得
+_文
+_他_
+_长
+_联合
+_过_
+_计
+_进行_
+法国_
+建设_
+_说
+题_
+重
+_政治
+_市
+里
+_解
+_政府
+口
+要
+_均
+发展_
+联合国
+_组
+几_
+_我们_
+后_
+_经
+_美
+来_
+合国_
+济_
+口_
+”_
+元
+＃
+府_
+军民
+并_
+职工
+_８
+成_
+约_
+_等
+级_
+次_
+_社会主
+_２
+_政治_
+_”_
+_英
+得了_
+_＃
+_发展_
+_社
+生产
+_条
+军民_
+”
+_职
+_取得了
+_联
+就_
+_我们
+发展
+两
+议
+_小
+_联合国
diff --git a/libtextcat/data/new_fingerprints/lm/chinese_traditional.lm b/libtextcat/data/new_fingerprints/lm/chinese_traditional.lm
new file mode 100644
index 000000000000..6708981ba6e7
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/chinese_traditional.lm
@@ -0,0 +1,400 @@
+_
+﹐_
+_﹐_
+﹐
+_﹐
+的
+_的
+的_
+_的_
+。
+_。
+。_
+_。_
+年
+_會
+會_
+_會_
+年_
+_年_
+十
+電
+會
+_年
+_在
+電_
+_是_
+_電_
+一
+於
+學_
+_於_
+_於
+在
+_電
+學
+是_
+港
+_學_
+在_
+_是
+於_
+_在_
+_學
+是
+不_
+_十
+_不
+_港_
+_港
+_不_
+十_
+_一
+員
+員_
+_一_
+不
+_十_
+一_
+港_
+_署
+_員_
+_員
+_業
+業
+_署_
+業_
+_業_
+署_
+署
+_事
+_同
+機
+_國_
+，
+、
+_，_
+_內
+、_
+_外_
+_同_
+_政_
+_公_
+為
+外
+公
+_公
+有
+_內_
+同
+_政
+國_
+國
+公_
+香
+_事_
+外_
+事
+內_
+_，
+_、
+政
+_外
+_、_
+香_
+政_
+內
+同_
+事_
+，_
+_國
+為_
+_長_
+_較_
+_方_
+_用_
+等_
+獲
+錦
+_文_
+_中
+_錦
+用
+_通
+_較
+_等
+有_
+_長
+_路
+通
+_警_
+_及
+_及_
+_警
+_香
+錦_
+_訴
+中_
+_話
+_有_
+通_
+時_
+獲_
+_予
+路_
+較_
+方_
+田
+警
+機_
+_訴_
+_田_
+等
+_有
+話_
+_機_
+_予_
+路
+時
+方
+日
+警_
+_通_
+訴_
+_用
+_方
+及_
+田_
+_話_
+_中_
+_香_
+訴
+_田
+_文
+_錦_
+三
+較
+用_
+_時_
+中
+_等_
+及
+話
+_機
+_獲
+九
+文
+_時
+_路_
+_獲_
+長
+_為_
+_為
+予
+長_
+予_
+文_
+_日_
+九_
+途_
+_高
+裝_
+故_
+_室
+_發_
+_控_
+前_
+回：
+_查_
+_三
+_安
+_以
+_控
+途
+_安_
+_裝
+_士_
+_雇
+_大_
+_上_
+_起
+出_
+_三_
+_人_
+_起_
+室_
+_人
+_分_
+_至_
+上_
+_出_
+第
+_*
+至
+_查
+程
+_煙_
+_生_
+_以_
+_只
+者
+_可
+三_
+_*_
+分_
+_途
+_前
+_分
+_線_
+_出
+發
+_與_
+生
+由
+可_
+煙_
+_由_
+_線
+者_
+至_
+日_
+只_
+煙
+發_
+_使
+_使_
+查
+_第
+_雇_
+以_
+_只_
+控_
+安_
+*
+與_
+線
+_與
+_至
+改
+人_
+大_
+_上
+_高_
+故
+起_
+高
+線_
+大
+控
+士
+_故_
+_作_
+使
+_由
+由_
+_途_
+安
+作
+*_
+以
+_生
+來
+_大
+回
+_日
+_前_
+四
+_九_
+_九
+人
+_裝_
+上
+_發
+_作
+士_
+_故
+作_
+高_
+雇
+只
+可
+：
+裝
+使_
+起
+出
+前
+_煙
+_可_
+雇_
+_室_
+生_
+八
+_士
+查_
+分
+室
+與
+也_
+肇_
+和_
+_物_
+_如_
+_霧_
+主_
+_商_
+約
+_府_
+到_
+達
+道
+都_
+黨_
+過
+_重_
+_者_
+未_
+_修_
+_約_
+別_
+郵_
+_能_
+來_
+_霧
+_車
+－
+_司_
+_排
+_該_
+_柙_
+被_
+總_
+_越
+呎_
+_資
+_排_
+期_
+_夜_
+_修
+巴_
+_育_
+_歌_
+_號_
+_圍_
+_調
+_亦_
+_校
+_)
+_後_
+入_
+_便
+_訊
+_期_
+脹_
+_而_
+_重
+o
+_該
+_o
+_(
+程_
diff --git a/libtextcat/data/new_fingerprints/lm/croatian.lm b/libtextcat/data/new_fingerprints/lm/croatian.lm
new file mode 100644
index 000000000000..b054ac34ab89
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/croatian.lm
@@ -0,0 +1,400 @@
+_	 36598
+a	 9456
+o	 9050
+i	 8526
+e	 7955
+n	 5513
+j	 5379
+s	 4971
+t	 4125
+r	 3889
+u	 3423
+je	 3281
+l	 3231
+e_	 3177
+d	 3128
+k	 2992
+v	 2891
+a_	 2835
+o_	 2679
+m	 2645
+p	 2316
+_s	 2212
+i_	 2205
+y	 2174
+c	 1894
+z	 1867
+je_	 1613
+_n	 1593
+g	 1581
+_p	 1490
+b	 1386
+u_	 1382
+,	 1208
+,_	 1208
+st	 1203
+_j	 1202
+na	 1159
+_je	 1118
+_d	 1105
+_i	 1104
+.	 1069
+._	 1058
+ra	 1017
+ko	 981
+ni	 980
+_je_	 918
+ij	 914
+ti	 911
+no	 891
+da	 884
+to	 879
+_k	 863
+_o	 856
+cy	 839
+li	 838
+ne	 790
+sy	 786
+-	 785
+pr	 760
+_u	 748
+po	 734
+ta	 711
+_b	 705
+_t	 704
+la	 699
+ja	 699
+an	 691
+m_	 680
+ov	 674
+ije	 673
+_z	 669
+ka	 662
+ri	 652
+lo	 651
+vo	 643
+re	 641
+is	 626
+in	 623
+se	 623
+va	 622
+_m	 617
+oj	 614
+_po	 594
+_pr	 592
+bi	 588
+en	 582
+il	 578
+os	 576
+vi	 572
+nj	 569
+ak	 564
+_na	 558
+im	 558
+da_	 553
+od	 550
+ao	 550
+al	 549
+om	 545
+na_	 533
+_se	 524
+_i_	 523
+h	 517
+_g	 511
+ma	 508
+at	 502
+cj	 501
+og	 497
+--	 493
+ro	 493
+on	 485
+av	 480
+_da	 474
+_ne	 474
+ed	 472
+zy	 471
+se_	 466
+_se_	 458
+_bi	 457
+ao_	 452
+ad	 452
+lj	 445
+es	 444
+ji	 441
+_v	 433
+_c	 430
+za	 421
+go	 418
+_r	 413
+_u_	 411
+yi	 410
+ek	 406
+di	 403
+sa	 396
+et	 393
+ic	 391
+io	 390
+_da_	 389
+to_	 389
+as	 386
+_ko	 383
+ye	 378
+ar	 378
+mo	 373
+le	 367
+or	 364
+ju	 363
+el	 354
+tr	 354
+io_	 352
+ve	 345
+lo_	 344
+su	 344
+ol	 344
+am	 344
+iz	 343
+li_	 338
+ti_	 336
+sto	 323
+n_	 321
+it	 319
+_za	 319
+sta	 317
+_ni	 316
+te	 312
+nu	 312
+a,	 309
+a,_	 309
+ya	 309
+do	 304
+om_	 303
+la_	 300
+no_	 299
+_na_	 299
+d_	 297
+ko_	 296
+aj	 294
+ik	 292
+ru	 291
+ga	 291
+em	 288
+nje	 283
+dj	 281
+ne_	 281
+k_	 277
+_st	 276
+koj	 276
+ec	 274
+_ka	 272
+_su	 270
+ob	 265
+-_	 263
+az	 261
+sv	 260
+_koj	 260
+im_	 260
+ije_	 259
+pa	 258
+ot	 257
+yt	 256
+ok	 255
+su_	 255
+ih	 254
+me	 253
+dn	 253
+_cy	 253
+iv	 251
+syt	 248
+g_	 247
+--_	 246
+_-	 246
+kr	 246
+---	 246
+a.	 245
+e,_	 245
+---_	 245
+e,	 245
+er	 245
+a._	 244
+_iz	 244
+mi	 243
+_---_	 242
+cyi	 242
+_--	 242
+_---	 242
+jed	 240
+h_	 239
+_a	 239
+_sa	 237
+j_	 236
+_l	 231
+_sv	 229
+_to	 229
+sk	 228
+ih_	 224
+ja_	 223
+pro	 223
+yn	 222
+t_	 222
+ost	 221
+_do	 221
+oc	 219
+gl	 218
+_su_	 216
+og_	 216
+uc	 214
+s_	 214
+bil	 213
+oz	 213
+ki	 212
+ni_	 212
+nij	 209
+ako	 208
+eg	 208
+ut	 205
+pre	 205
+ci	 204
+ji_	 203
+_od	 203
+ilo	 202
+ati	 202
+ac	 201
+ns	 200
+_mo	 197
+rij	 196
+bo	 195
+ovo	 195
+ku	 195
+dje	 194
+ma_	 192
+_bil	 191
+cje	 186
+sti	 186
+_go	 186
+de	 185
+sl	 183
+_pro	 182
+ju_	 182
+nije	 181
+tv	 180
+lje	 179
+isy	 179
+pri	 178
+_pre	 177
+dr	 177
+e._	 177
+e.	 177
+op	 176
+ima	 176
+anj	 175
+jen	 175
+us	 172
+ilo_	 172
+_ra	 170
+S	 167
+ecj	 166
+iti	 166
+sp	 163
+_S	 161
+vr	 161
+i.	 161
+i._	 161
+zn	 161
+ali	 161
+i,_	 160
+i,	 160
+ap	 157
+nije_	 157
+nst	 156
+pi	 156
+ga_	 156
+_sy	 155
+_nj	 155
+jes	 155
+ran	 155
+vo_	 155
+yto	 154
+ev	 153
+_to_	 152
+_pri	 151
+est	 150
+N	 150
+ins	 150
+ist	 149
+ir	 149
+o,	 148
+vj	 148
+vje	 148
+o,_	 148
+B	 148
+zi	 147
+jec	 147
+gov	 147
+yto_	 147
+syto	 146
+ton	 146
+od_	 145
+O	 144
+rije	 144
+lik	 143
+on_	 142
+ocy	 142
+W	 142
+ba	 142
+_W	 141
+kao	 141
+Wi	 141
+_N	 141
+inst	 141
+_nij	 141
+_nije	 140
+_Wi	 140
+syto_	 140
+lic	 139
+P	 139
+ovi	 138
+_tr	 138
+rs	 137
+ez	 137
+edn	 136
+_P	 136
+si	 136
+ili	 136
+du	 136
+Winst	 135
+cye	 135
+nston	 135
+ston	 135
+ud	 135
+kao_	 135
+Wins	 135
+insto	 135
+oji	 135
+nsto	 135
+Win	 135
+raz	 135
+zye	 135
+_Win	 134
+ova	 134
+_Wins	 134
+_on	 133
+ako_	 133
+odi	 133
+cya	 133
+ila	 133
+icy	 133
+oj_	 133
+ke	 133
+va_	 132
+ija	 132
+_is	 132
+jel	 132
+oje	 130
+pu	 130
+cje_	 130
+bi_	 129
+rat	 128
+ce	 128
+tu	 128
+mu	 128
+ve_	 127
diff --git a/libtextcat/data/new_fingerprints/lm/czech.lm b/libtextcat/data/new_fingerprints/lm/czech.lm
new file mode 100644
index 000000000000..097bbc5b2241
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/czech.lm
@@ -0,0 +1,400 @@
+_	 26378
+o	 5870
+e	 5354
+a	 4740
+n	 4462
+t	 3745
+s	 3438
+i	 3187
+v	 3118
+l	 2891
+r	 2754
+k	 2566
+d	 2508
+m	 2198
+u	 2197
+p	 2032
+í	 1924
+c	 1678
+h	 1572
+z	 1544
+á	 1522
+_p	 1299
+e_	 1266
+y	 1231
+a_	 1219
+j	 1219
+_s	 1156
+b	 1079
+o_	 1065
+ě	 1043
+_v	 1038
+,	 952
+,_	 946
+st	 945
+_n	 911
+é	 878
+.	 870
+í_	 848
+ř	 822
+._	 803
+ní	 782
+ov	 757
+_z	 723
+i_	 716
+u_	 684
+ro	 674
+en	 656
+ý	 647
+ž	 639
+po	 630
+ch	 629
+č	 625
+na	 599
+_a	 598
+sk	 592
+š	 563
+ho	 552
+_d	 551
+ra	 545
+m_	 539
+y_	 530
+_t	 512
+ko	 504
+_k	 503
+le	 502
+_j	 501
+_o	 486
+to	 479
+pr	 471
+ne	 468
+ní_	 462
+je	 458
+é_	 456
+ti	 455
+od	 433
+li	 432
+va	 432
+_po	 429
+_m	 428
+al	 424
+te	 424
+ou	 423
+ed	 418
+se	 415
+la	 410
+no	 397
+os	 382
+lo	 377
+an	 376
+_pr	 375
+ů	 375
+v_	 372
+ře	 370
+_a_	 364
+em	 363
+at	 360
+ta	 359
+do	 357
+t_	 357
+_b	 355
+or	 349
+h_	 345
+_v_	 338
+ch_	 327
+S	 325
+ce	 323
+av	 323
+př	 322
+ni	 319
+ké	 316
+er	 315
+ně	 315
+_na	 313
+na_	 312
+_ne	 311
+de	 308
+ic	 307
+in	 306
+_se	 306
+l_	 304
+dn	 302
+za	 298
+_př	 293
+ě_	 291
+ol	 290
+_je	 281
+ob	 280
+is	 277
+ve	 274
+ho_	 272
+es	 270
+ot	 268
+ak	 265
+vo	 263
+ná	 260
+il	 257
+se_	 257
+it	 256
+et	 253
+ad	 250
+by	 249
+P	 242
+_r	 242
+k_	 242
+ost	 241
+_se_	 241
+tr	 238
+me	 237
+pro	 234
+že	 234
+ka	 230
+_za	 227
+om	 224
+el	 223
+_P	 223
+on	 218
+_pro	 216
+ou_	 216
+tu	 215
+O	 212
+mi	 212
+ku	 211
+_u	 210
+_do	 208
+_l	 207
+_na_	 206
+N	 205
+ské	 205
+ím	 205
+íc	 205
+ý_	 203
+mě	 203
+_S	 200
+oz	 200
+V	 200
+ze	 198
+da	 194
+sl	 192
+á_	 191
+ova	 190
+mo	 190
+re	 189
+so	 187
+vy	 186
+ej	 185
+rá	 184
+ar	 184
+s_	 183
+vě	 183
+A	 181
+ru	 180
+_st	 178
+f	 178
+éh	 177
+ého	 176
+kt	 176
+tn	 175
+g	 174
+bo	 174
+ez	 173
+ci	 172
+ký	 172
+né	 170
+M	 170
+án	 169
+as	 168
+vi	 167
+ři	 167
+ac	 166
+že_	 165
+ýc	 165
+ž_	 165
+ck	 164
+K	 164
+B	 164
+ých	 164
+vá	 162
+_c	 162
+ého_	 162
+ení	 161
+lá	 160
+_ž	 160
+ří	 160
+pře	 159
+ec	 158
+ů_	 157
+J	 156
+vn	 156
+_h	 155
+ké_	 155
+ok	 154
+sta	 154
+to_	 152
+vý	 152
+nt	 151
+ých_	 149
+lo_	 149
+_by	 149
+dy	 149
+_pře	 148
+ce_	 147
+R	 146
+n_	 146
+ád	 146
+pa	 145
+vé	 145
+am	 145
+mu	 145
+ný	 145
+ud	 144
+_č	 144
+_B	 142
+ter	 141
+ně_	 141
+če	 140
+še	 140
+_V	 140
+_ko	 140
+li_	 139
+dě	 137
+hl	 137
+je_	 137
+ji	 137
+ist	 135
+jí	 135
+-	 134
+ik	 133
+si	 133
+ál	 132
+em_	 132
+_to	 132
+_vy	 131
+sp	 130
+ut	 130
+_J	 130
+_že	 130
+_M	 129
+di	 129
+kon	 128
+la_	 128
+tí	 128
+_ro	 127
+ns	 127
+ek	 126
+ick	 126
+T	 126
+yl	 125
+čn	 125
+rn	 125
+_že_	 124
+op	 124
+sti	 124
+kte	 124
+řed	 124
+edn	 123
+us	 121
+ím_	 120
+"	 119
+z_	 119
+str	 118
+ti_	 118
+ém	 118
+vat	 118
+d_	 118
+_ve	 118
+áv	 118
+ení_	 117
+iv	 117
+oj	 117
+_kt	 117
+ěl	 117
+val	 116
+eb	 116
+_K	 115
+tř	 115
+_kte	 115
+át	 115
+_i	 114
+_N	 114
+D	 114
+kl	 114
+ny	 114
+byl	 113
+ev	 113
+ri	 113
+ú	 113
+ky	 111
+sm	 111
+oh	 111
+E	 110
+ma	 110
+ět	 110
+ský	 110
+kter	 109
+nu	 109
+le_	 108
+ja	 107
+zá	 107
+tě	 106
+tá	 106
+zn	 106
+let	 105
+aj	 105
+sto	 105
+ší	 105
+me_	 105
+-_	 105
+u,	 105
+sv	 104
+_le	 104
+pol	 104
+L	 104
+_-	 104
+ln	 104
+pod	 104
+H	 103
+zi	 103
+kéh	 103
+kého	 103
+_ná	 103
+ent	 102
+u,_	 102
+_od	 102
+né_	 101
+_-_	 101
+al_	 101
+_kter	 101
+do_	 100
+nos	 100
+cí	 100
+rav	 99
+ran	 99
+_sv	 99
+ká	 98
+eč	 98
+ním	 98
+bu	 97
+_z_	 97
+ích	 97
+_byl	 97
+ání	 96
+rov	 96
+kr	 96
+dá	 95
+ové	 95
+dl	 95
+uj	 95
+nost	 95
+ém_	 95
+ech	 94
+ly	 94
+oc	 94
+vé_	 93
+_o_	 93
+dy_	 93
+ak_	 93
+nsk	 93
+_so	 93
+_ob	 92
+nc	 92
diff --git a/libtextcat/data/new_fingerprints/lm/danish.lm b/libtextcat/data/new_fingerprints/lm/danish.lm
new file mode 100644
index 000000000000..5e5a61a98638
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/danish.lm
@@ -0,0 +1,400 @@
+_	 21274
+e	 9291
+r	 5307
+n	 4733
+i	 3976
+t	 3948
+s	 3751
+a	 3296
+l	 3063
+d	 3025
+o	 2868
+g	 2471
+er	 2164
+k	 2002
+m	 1680
+e_	 1655
+en	 1613
+f	 1507
+de	 1484
+r_	 1379
+v	 1245
+u	 1176
+t_	 1081
+n_	 1032
+er_	 992
+b	 942
+.	 870
+ge	 868
+._	 831
+re	 816
+h	 816
+et	 813
+te	 813
+p	 806
+in	 788
+or	 775
+_s	 753
+_a	 749
+en_	 712
+_e	 691
+ti	 689
+an	 687
+,	 681
+,_	 677
+_f	 655
+_d	 645
+el	 642
+ng	 635
+nd	 634
+g_	 634
+se	 615
+le	 615
+st	 607
+s_	 601
+_o	 572
+ne	 560
+li	 537
+et_	 524
+es	 521
+_i	 512
+ri	 511
+sk	 510
+_de	 498
+å	 497
+ar	 475
+ed	 473
+ig	 463
+at	 452
+_m	 446
+is	 443
+fo	 441
+æ	 441
+ve	 438
+_k	 434
+ø	 432
+der	 429
+ke	 428
+ing	 427
+og	 426
+_b	 412
+me	 408
+il	 407
+for	 405
+ns	 394
+y	 389
+_h	 380
+_t	 374
+on	 371
+d_	 370
+al	 362
+be	 359
+_fo	 351
+af	 336
+de_	 335
+_og	 333
+_p	 332
+og_	 325
+om	 325
+_for	 324
+_og_	 313
+l_	 308
+nge	 302
+i_	 295
+_v	 294
+c	 289
+ter	 283
+ll	 280
+ni	 278
+nde	 278
+rs	 277
+_af	 277
+un	 275
+ra	 271
+ko	 271
+den	 270
+_i_	 268
+id	 265
+til	 265
+j	 265
+vi	 264
+D	 260
+ere	 256
+ma	 255
+si	 253
+f_	 252
+af_	 238
+_af_	 235
+ik	 235
+m_	 234
+å_	 232
+_ti	 227
+_D	 226
+_u	 226
+_er	 225
+nt	 224
+_en	 224
+ls	 221
+es_	 216
+lig	 216
+ger	 216
+re_	 210
+ag	 210
+_me	 207
+at_	 204
+lle	 200
+ge_	 200
+_til	 200
+ige	 199
+_er_	 199
+der_	 199
+em	 199
+ds	 197
+r.	 195
+io	 195
+r._	 195
+ud	 193
+_at	 192
+_at_	 191
+ta	 190
+els	 190
+_l	 190
+ha	 190
+il_	 189
+or_	 189
+ke_	 186
+rt	 185
+gen	 184
+ka	 183
+-	 180
+rk	 180
+ning	 178
+ol	 178
+nin	 178
+la	 177
+ld	 175
+De	 175
+it	 173
+ede	 172
+ed_	 171
+_ko	 171
+lse	 171
+ek	 168
+else	 167
+inge	 167
+på	 167
+ng_	 167
+_på	 167
+iv	 166
+ør	 166
+so	 165
+he	 165
+ens	 165
+ske	 165
+ind	 164
+til_	 163
+rn	 163
+ide	 162
+ev	 162
+den_	 162
+to	 162
+sen	 160
+_be	 160
+sa	 160
+bl	 158
+_g	 158
+an_	 157
+det	 156
+om_	 156
+ru	 156
+va	 155
+_til_	 155
+ste	 154
+rd	 153
+_på_	 152
+k_	 152
+på_	 152
+di	 152
+kr	 152
+K	 151
+_De	 149
+for_	 148
+te_	 148
+kon	 148
+ver	 147
+mm	 146
+am	 146
+_en_	 145
+_r	 145
+ne_	 144
+ing_	 144
+tr	 143
+le_	 142
+del	 142
+_in	 142
+gt	 140
+_st	 138
+S	 138
+eg	 138
+gs	 138
+tt	 138
+r,	 137
+ser	 137
+r,_	 137
+er.	 137
+ro	 137
+er._	 137
+_for_	 136
+ent	 136
+kt	 136
+eri	 135
+ur	 134
+lin	 134
+B	 133
+A	 133
+sti	 133
+ner	 133
+da	 133
+ris	 132
+ion	 132
+_K	 131
+ern	 131
+ers	 130
+ist	 130
+ær	 130
+ige_	 130
+_si	 130
+tte	 129
+E	 128
+_n	 128
+nn	 127
+_B	 126
+_ha	 126
+_.	 126
+rne	 125
+H	 125
+_ud	 125
+rin	 124
+na	 124
+und	 124
+ft	 124
+_der	 124
+ku	 123
+_A	 122
+ler	 120
+and	 120
+end	 120
+ns_	 120
+rg	 119
+op	 119
+er,_	 119
+er,	 119
+ar_	 118
+P	 118
+_S	 117
+_H	 117
+_._	 116
+ov	 116
+erne	 115
+tio	 115
+med	 115
+tion	 115
+_E	 115
+_P	 115
+det_	 114
+pr	 114
+e.	 113
+ter_	 113
+:	 113
+kk	 113
+e._	 113
+e,_	 113
+e,	 113
+od	 113
+kke	 113
+ten	 113
+ling	 113
+:_	 112
+mi	 112
+eli	 112
+lo	 111
+som	 111
+_den	 111
+rb	 110
+se_	 110
+ell	 110
+sid	 110
+nne	 109
+fi	 108
+lt	 107
+v_	 107
+_de_	 107
+ark	 106
+lige	 106
+ngen	 106
+ie	 105
+_med	 105
+_der_	 105
+ring	 105
+a_	 105
+_vi	 104
+-_	 104
+ys	 103
+gel	 103
+_so	 103
+ia	 103
+ive	 102
+ej	 101
+ati	 101
+ren	 101
+_det	 101
+side	 101
+ske_	 101
+br	 100
+gi	 100
+F	 100
+M	 100
+ul	 99
+isk	 99
+men	 99
+n,_	 99
+age	 99
+fr	 99
+n,	 99
+tu	 98
+ts	 98
+_ma	 98
+nder	 98
+ot	 97
+dt	 97
+R	 97
+med_	 96
+ho	 96
+ans	 95
+_kon	 95
+pe	 95
+ce	 94
+gr	 93
+mme	 92
+ret	 92
+lige_	 92
+mu	 91
+_med_	 91
+hv	 91
+væ	 91
+Det	 91
+ens_	 91
+kl	 91
+_M	 90
+T	 90
+ingen	 90
+rm	 90
+ill	 89
+elle	 89
+ef	 89
+ene	 89
+nds	 89
+ove	 89
+som_	 89
+C	 88
+_den_	 88
diff --git a/libtextcat/data/new_fingerprints/lm/drents.lm b/libtextcat/data/new_fingerprints/lm/drents.lm
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/drents.lm
diff --git a/libtextcat/data/new_fingerprints/lm/dutch.lm b/libtextcat/data/new_fingerprints/lm/dutch.lm
new file mode 100644
index 000000000000..17a0626982a5
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/dutch.lm
@@ -0,0 +1,400 @@
+_	 20104
+e	 9848
+n	 5323
+a	 3733
+t	 3683
+i	 3490
+r	 3195
+d	 2876
+o	 2845
+n_	 2443
+en	 2439
+s	 2195
+e_	 1842
+l	 1837
+g	 1522
+en_	 1500
+de	 1489
+er	 1388
+t_	 1377
+v	 1253
+u	 1217
+k	 1204
+_d	 1136
+h	 1102
+m	 1084
+an	 939
+te	 875
+j	 857
+in	 810
+_v	 793
+r_	 751
+de_	 742
+ee	 737
+p	 732
+et	 718
+ge	 716
+aa	 708
+b	 703
+_e	 686
+st	 669
+z	 668
+ie	 662
+_de	 655
+w	 631
+c	 611
+.	 604
+s_	 582
+_de_	 576
+_h	 572
+el	 570
+ij	 564
+._	 554
+et_	 531
+an_	 522
+he	 505
+_o	 497
+nd	 478
+_i	 475
+ar	 459
+_m	 451
+re	 442
+ve	 441
+'	 428
+or	 424
+ng	 421
+at	 418
+_s	 415
+oo	 403
+_z	 401
+le	 395
+_b	 394
+_a	 391
+_he	 386
+va	 385
+er_	 381
+me	 372
+_w	 368
+f	 361
+on	 351
+_t	 351
+_va	 345
+_g	 342
+di	 342
+nt	 340
+,	 335
+g_	 335
+,_	 334
+van	 327
+ch	 326
+is	 326
+ing	 325
+be	 325
+ni	 320
+it	 317
+een	 316
+_van	 315
+al	 310
+den	 309
+ti	 309
+van_	 307
+oe	 302
+ke	 302
+_van_	 299
+aar	 299
+d_	 295
+we	 293
+da	 292
+tu	 290
+_ee	 290
+ud	 287
+een_	 286
+li	 284
+es	 282
+_st	 281
+ver	 281
+ten	 281
+ri	 275
+nde	 275
+der	 274
+_in	 270
+k_	 268
+vo	 267
+het	 266
+oor	 264
+_het	 262
+het_	 262
+_het_	 259
+_een	 258
+l_	 258
+ze	 257
+_n	 254
+ro	 248
+gen	 243
+_een_	 241
+at_	 240
+op	 238
+n.	 238
+_en	 237
+rs	 237
+_da	 235
+stu	 232
+in_	 230
+_be	 229
+_ge	 228
+_k	 226
+rd	 226
+tud	 220
+_en_	 220
+n._	 217
+te_	 209
+ei	 208
+ent	 206
+_me	 203
+la	 202
+ek	 202
+ed	 201
+ra	 200
+stud	 200
+en.	 200
+ie_	 197
+ste	 196
+_vo	 195
+_in_	 193
+_stu	 191
+zi	 191
+om	 189
+ui	 189
+en._	 186
+ten_	 185
+_stud	 185
+ude	 184
+die	 183
+ns	 183
+_j	 181
+D	 179
+aan	 179
+se	 179
+ma	 178
+_ve	 176
+ne	 174
+_p	 174
+eg	 173
+p_	 172
+ar_	 172
+aar_	 171
+_te	 170
+ng_	 169
+_we	 169
+''	 167
+_D	 165
+ers	 164
+_op	 163
+dat	 161
+dat_	 160
+ig	 160
+ere	 159
+eer	 158
+_zi	 158
+voor	 156
+voo	 156
+nge	 155
+nder	 151
+nte	 151
+or_	 150
+ta	 150
+je	 149
+ing_	 148
+ll	 148
+_ver	 147
+jk	 146
+oor_	 146
+_dat	 145
+ijk	 145
+ren	 145
+is_	 145
+_dat_	 144
+_l	 144
+and	 144
+lij	 143
+ter	 143
+na	 142
+uden	 139
+tude	 138
+_voor	 136
+_voo	 136
+ond	 136
+ken	 135
+cht	 135
+_al	 135
+ht	 135
+wa	 134
+ho	 133
+em	 133
+den_	 133
+pe	 132
+sc	 132
+un	 131
+ur	 131
+_di	 130
+gen_	 130
+zo	 129
+rt	 129
+ev	 128
+mo	 128
+lijk	 127
+_is	 126
+stude	 124
+ha	 123
+to	 122
+el_	 121
+og	 121
+op_	 121
+sch	 120
+ol	 120
+ente	 119
+_u	 118
+pr	 118
+end	 118
+mi	 117
+iet	 116
+_aa	 116
+eli	 115
+dent	 115
+ijn	 115
+jn	 115
+ou	 115
+men	 114
+_'	 114
+tie	 113
+_is_	 113
+nie	 113
+tr	 112
+ak	 112
+id	 112
+udent	 111
+tuden	 111
+uit	 110
+_te_	 109
+aan_	 109
+ld	 109
+S	 108
+_aan	 108
+ede	 108
+ja	 107
+nten	 107
+it_	 107
+je_	 107
+ts	 107
+erd	 106
+est	 106
+E	 105
+_op_	 105
+ad	 104
+al_	 104
+_ze	 104
+_on	 104
+rk	 104
+lle	 103
+ens	 103
+gel	 103
+m_	 103
+len	 103
+_r	 102
+ec	 102
+inge	 102
+met	 102
+_met	 101
+si	 100
+die_	 100
+us	 100
+onde	 99
+_ni	 99
+De	 99
+eu	 99
+dente	 99
+enten	 99
+ic	 99
+_met_	 98
+f_	 98
+met_	 98
+no	 97
+ko	 96
+voor_	 96
+rde	 96
+H	 96
+ngen	 95
+lo	 95
+ot	 95
+as	 94
+zij	 93
+_nie	 92
+vi	 92
+eb	 92
+_De	 92
+_zij	 91
+ep	 91
+wi	 91
+_zo	 91
+kt	 91
+ege	 91
+G	 91
+bi	 90
+j_	 90
+ij_	 90
+ze_	 90
+do	 90
+lan	 89
+ov	 89
+udi	 89
+ord	 89
+onder	 89
+V	 88
+elij	 88
+_wa	 88
+elijk	 88
+ef	 88
+_die	 87
+ag	 86
+erk	 86
+eren	 86
+R	 85
+ik	 85
+_ma	 85
+gr	 85
+am	 85
+_mo	 84
+ul	 84
+nn	 83
+eve	 83
+De_	 83
+maa	 83
+ingen	 83
+wo	 83
+_''	 83
+O	 83
+tudi	 82
+I	 82
+nt_	 82
+tudie	 81
+ven	 81
+udie	 81
+nten_	 81
+_die_	 81
+jaa	 80
+ka	 80
+eke	 80
+ite	 80
+a_	 80
+_je	 80
+ac	 80
+jaar	 80
+_je_	 79
+_H	 79
+_zijn	 79
+zijn	 79
+n,	 78
+nen	 78
+N	 78
+n,_	 78
+ijn_	 77
diff --git a/libtextcat/data/new_fingerprints/lm/english.lm b/libtextcat/data/new_fingerprints/lm/english.lm
new file mode 100644
index 000000000000..ab71632c6214
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/english.lm
@@ -0,0 +1,400 @@
+_	 20326
+e	 6617
+t	 4843
+o	 3834
+n	 3653
+i	 3602
+a	 3433
+s	 2945
+r	 2921
+h	 2507
+e_	 2000
+d	 1816
+_t	 1785
+c	 1639
+l	 1635
+th	 1535
+he	 1351
+_th	 1333
+u	 1309
+f	 1253
+m	 1175
+p	 1151
+_a	 1145
+the	 1142
+_the	 1060
+s_	 978
+er	 968
+_o	 967
+he_	 928
+d_	 888
+t_	 885
+the_	 844
+_the_	 843
+on	 842
+in	 817
+y	 783
+n_	 773
+b	 761
+re	 754
+,	 734
+,_	 732
+an	 732
+g	 728
+w	 718
+_i	 707
+en	 676
+f_	 599
+y_	 595
+of	 594
+_of	 592
+es	 589
+ti	 587
+v	 580
+_of_	 575
+of_	 575
+nd	 568
+at	 549
+r_	 540
+_w	 534
+it	 522
+ed	 496
+_p	 494
+nt	 485
+_c	 462
+o_	 457
+io	 450
+_an	 439
+te	 432
+or	 425
+_b	 418
+nd_	 407
+to	 406
+st	 402
+is	 401
+_s	 396
+_in	 389
+ion	 385
+and	 385
+de	 384
+ve	 382
+ha	 375
+ar	 366
+_m	 361
+and_	 360
+_and	 360
+_and_	 358
+se	 353
+_to	 347
+me	 346
+to_	 344
+ed_	 339
+.	 330
+be	 329
+_f	 329
+._	 329
+_to_	 320
+co	 317
+ic	 316
+ns	 308
+al	 307
+le	 304
+ou	 304
+ce	 293
+ent	 279
+l_	 278
+_co	 277
+tio	 275
+on_	 274
+_d	 274
+tion	 268
+ri	 266
+_e	 264
+ng	 253
+hi	 251
+er_	 249
+ea	 246
+as	 245
+_be	 242
+pe	 242
+h_	 234
+_r	 232
+ec	 227
+ch	 223
+ro	 222
+ct	 220
+_h	 219
+pr	 217
+in_	 217
+ne	 214
+ll	 214
+rt	 213
+s,_	 210
+s,	 210
+li	 209
+ra	 208
+T	 207
+wh	 204
+a_	 203
+ac	 201
+_wh	 199
+_n	 196
+ts	 196
+di	 196
+es_	 195
+si	 194
+re_	 193
+at_	 192
+nc	 192
+ie	 190
+_a_	 188
+_in_	 185
+ing	 184
+us	 182
+_re	 182
+g_	 179
+ng_	 178
+op	 178
+con	 177
+tha	 175
+_l	 174
+_tha	 174
+ver	 173
+ma	 173
+ion_	 171
+_con	 171
+ci	 170
+ons	 170
+_it	 170
+po	 169
+ere	 168
+is_	 167
+ta	 167
+la	 166
+_pr	 165
+fo	 164
+ho	 164
+ir	 162
+ss	 161
+men	 160
+be_	 160
+un	 159
+ty	 159
+_be_	 158
+ing_	 157
+om	 156
+ot	 156
+hat	 155
+ly	 155
+_g	 155
+em	 153
+_T	 151
+rs	 150
+mo	 148
+ch_	 148
+wi	 147
+we	 147
+ad	 147
+ts_	 145
+res	 143
+_wi	 143
+I	 143
+hat_	 142
+ei	 141
+ly_	 141
+ni	 140
+os	 140
+ca	 139
+ur	 139
+A	 138
+ut	 138
+that	 138
+_that	 137
+ati	 137
+_fo	 137
+st_	 137
+il	 136
+or_	 136
+for	 136
+pa	 136
+ul	 135
+ate	 135
+ter	 134
+it_	 134
+nt_	 133
+that_	 132
+_ha	 129
+al_	 128
+el	 128
+as_	 127
+ll_	 127
+_ma	 125
+no	 124
+ment	 124
+an_	 124
+tion_	 122
+su	 122
+bl	 122
+_de	 122
+nce	 120
+pl	 120
+fe	 119
+tr	 118
+so	 118
+int	 115
+ov	 114
+e,	 114
+e,_	 114
+_u	 113
+ent_	 113
+Th	 113
+her	 113
+j	 112
+atio	 112
+ation	 112
+_Th	 111
+le_	 110
+ai	 110
+_it_	 110
+_on	 110
+_for	 109
+ect	 109
+k	 109
+hic	 108
+est	 108
+der	 107
+tu	 107
+na	 106
+_by_	 106
+by_	 106
+E	 106
+by	 106
+_by	 106
+ve_	 106
+_di	 106
+en_	 104
+vi	 104
+m_	 103
+_whi	 102
+iv	 102
+whi	 102
+ns_	 102
+_A	 101
+ich	 100
+ge	 100
+pro	 99
+ess	 99
+_whic	 99
+ers	 99
+hich	 99
+ce_	 99
+which	 99
+whic	 99
+all	 98
+ove	 98
+_is	 98
+ich_	 97
+ee	 97
+hich_	 97
+n,_	 96
+n,	 96
+im	 95
+ir_	 94
+hei	 94
+ions	 94
+sti	 94
+se_	 94
+per	 93
+The	 93
+_pa	 93
+heir	 93
+id	 93
+eir	 93
+eir_	 93
+ig	 93
+heir_	 93
+_no	 93
+ev	 93
+era	 92
+_int	 92
+ted	 91
+_The	 91
+ies	 91
+art	 91
+thei	 90
+_ar	 90
+_thei	 90
+their	 90
+_pro	 90
+et	 89
+_pe	 88
+_mo	 88
+ther	 88
+x	 87
+gh	 87
+S	 87
+_is_	 87
+ol	 87
+ty_	 87
+_I	 86
+nde	 86
+am	 86
+rn	 86
+nte	 86
+mp	 85
+_su	 84
+_we	 84
+par	 84
+_v	 84
+pu	 82
+his	 82
+ow	 82
+mi	 82
+go	 81
+N	 81
+ue	 81
+ple	 81
+ep	 80
+ab	 80
+;_	 80
+;	 80
+ex	 80
+ain	 80
+over	 80
+_un	 79
+q	 79
+qu	 79
+pp	 79
+ith	 79
+ry	 79
+_as	 79
+ber	 79
+ub	 78
+av	 78
+uc	 78
+s._	 77
+s.	 77
+enc	 77
+are	 77
+iti	 77
+gr	 76
+his_	 76
+ua	 76
+part	 76
+ff	 75
+eve	 75
+O	 75
+rea	 74
+ous	 74
+ia	 74
+The_	 73
+ag	 73
+mb	 73
+_go	 73
+fa	 72
+on,_	 72
+ern	 72
+t,_	 72
+on,	 72
+t,	 72
+_me	 71
diff --git a/libtextcat/data/new_fingerprints/lm/esperanto.lm b/libtextcat/data/new_fingerprints/lm/esperanto.lm
new file mode 100644
index 000000000000..0eef3ec8894a
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/esperanto.lm
@@ -0,0 +1,400 @@
+_	 57050
+a	 16035
+i	 12706
+e	 12227
+o	 12102
+n	 10393
+s	 8344
+l	 7707
+r	 7492
+t	 7134
+k	 5376
+u	 4558
+j	 3946
+a_	 3875
+m	 3783
+d	 3710
+p	 3693
+la	 2840
+s_	 2769
+e_	 2751
+.	 2706
+_l	 2635
+_k	 2619
+v	 2531
+n_	 2504
+o_	 2444
+i_	 2333
+._	 2278
+on	 2238
+,	 2193
+,_	 2182
+_la	 2100
+en	 2080
+j_	 2050
+as	 2028
+la_	 2012
+ta	 1956
+_la_	 1907
+an	 1882
+_p	 1850
+g	 1831
+_e	 1791
+_d	 1778
+is	 1737
+aj	 1658
+st	 1635
+_s	 1575
+c	 1526
+de	 1517
+oj	 1498
+er	 1476
+ti	 1456
+f	 1443
+_a	 1442
+b	 1427
+ro	 1379
+_m	 1351
+ra	 1341
+nt	 1293
+ka	 1270
+ri	 1258
+al	 1249
+as_	 1248
+aj_	 1213
+to	 1209
+_de	 1203
+_t	 1200
+te	 1179
+_n	 1176
+is_	 1171
+in	 1151
+ko	 1145
+or	 1114
+es	 1083
+re	 1034
+ia	 1029
+li	 1022
+de_	 1016
+_de_	 979
+ar	 974
+_v	 966
+vi	 942
+lo	 932
+x	 928
+io	 917
+ne	 855
+no	 848
+ni	 843
+mi	 835
+ma	 819
+_ka	 816
+el	 815
+pr	 771
+z	 744
+un	 734
+l_	 732
+po	 730
+_f	 725
+ø	 724
+est	 691
+na	 687
+ki	 679
+kaj	 676
+si	 665
+u_	 663
+kaj_	 660
+"	 654
+tas	 651
+le	 650
+oj_	 648
+_i	 643
+tr	 642
+_pr	 630
+_es	 628
+jn	 626
+pe	 618
+_kaj	 616
+ig	 616
+_kaj_	 611
+do	 608
+sta	 606
+on_	 602
+ek	 602
+ci	 597
+r_	 595
+ý	 594
+_r	 593
+il	 592
+_est	 587
+di	 586
+am	 586
+_mi	 582
+aý	 578
+_vi	 577
+mo	 575
+ant	 565
+_ne	 562
+en_	 561
+o.	 559
+æ	 543
+iu	 538
+o,	 529
+ur	 527
+o._	 527
+om	 525
+o,_	 524
+at	 521
+va	 521
+-	 519
+_en	 518
+:	 513
+:_	 512
+_ti	 500
+M	 496
+h	 488
+nd	 484
+me	 484
+_al	 481
+_ko	 479
+ve	 478
+ie	 478
+_ki	 473
+it	 473
+L	 466
+_b	 465
+se	 462
+em	 452
+ol	 450
+nta	 449
+tu	 448
+ik	 444
+ov	 443
+da	 443
+_M	 440
+_po	 439
+tas_	 438
+ne_	 437
+et	 437
+_ma	 436
+_en_	 435
+su	 429
+pl	 426
+_L	 425
+pa	 420
+_o	 417
+vo	 408
+an_	 407
+ro_	 406
+sti	 406
+nu	 399
+kon	 396
+stas	 391
+m_	 391
+ir	 388
+n.	 386
+fa	 386
+jn_	 382
+ku	 382
+os	 376
+ke	 375
+n,	 375
+esta	 374
+n,_	 372
+_su	 362
+ta_	 362
+stas_	 359
+xi	 359
+Mi	 358
+_ne_	 356
+al_	 355
+nk	 353
+so	 353
+n._	 352
+id	 349
+_g	 348
+estas	 347
+ga	 346
+_h	 345
+per	 345
+_Mi	 340
+ok	 339
+K	 339
+mp	 337
+_esta	 337
+s,_	 335
+s,	 335
+_se	 333
+anta	 332
+ul	 326
+ran	 325
+_"	 323
+ý_	 322
+te_	 320
+ak	 320
+aý_	 320
+ed	 320
+rt	 319
+ojn	 318
+gi	 318
+_æ	 317
+tis	 316
+gx	 316
+mal	 316
+ia_	 315
+ks	 310
+_al_	 310
+mi_	 309
+S	 309
+lu	 309
+ns	 308
+kt	 305
+io_	 302
+ent	 300
+?	 300
+_K	 300
+ec	 300
+el_	 299
+_-	 299
+li_	 299
+E	 298
+þ	 298
+_li	 297
+fo	 296
+ter	 296
+_re	 296
+A	 295
+nto	 294
+vi_	 292
+La	 292
+_mal	 290
+nte	 288
+sp	 287
+sa	 287
+_mi_	 279
+ut	 278
+op	 278
+_ke	 277
+bo	 277
+ajn	 276
+un_	 276
+T	 274
+to_	 272
+-_	 272
+bl	 272
+_an	 271
+_La	 271
+øi	 269
+_S	 268
+_pl	 267
+_fa	 266
+ni_	 266
+La_	 265
+_E	 264
+N	 263
+tis_	 263
+_tr	 263
+'	 262
+!	 262
+_-_	 262
+pro	 261
+iu_	 261
+iø	 261
+nc	 260
+_si	 259
+du	 257
+_kon	 256
+ru	 255
+_vi_	 254
+_j	 253
+ce	 251
+ke_	 249
+ap	 248
+us	 247
+be	 247
+im	 247
+B	 246
+_ku	 246
+_La_	 246
+tra	 245
+ad	 245
+uj	 245
+ac	 245
+ita	 243
+pre	 242
+_pro	 242
+co	 241
+rm	 241
+_ni	 238
+_pe	 236
+?_	 234
+on.	 234
+toj	 234
+"_	 234
+j.	 234
+_ke_	 233
+s.	 232
+_A	 231
+av	 230
+ri_	 230
+_el	 229
+por	 229
+`	 224
+ev	 224
+las	 223
+P	 223
+j._	 221
+eni	 220
+_T	 220
+_B	 219
+j,_	 218
+j,	 218
+era	 217
+_in	 216
+on._	 216
+cx	 216
+_N	 215
+ion	 215
+ab	 215
+..	 214
+)	 213
+fi	 213
+or_	 212
+pri	 212
+s._	 212
+_por	 210
+ez	 210
+in_	 210
+am_	 209
+on,_	 209
+ll	 209
+æi	 209
+on,	 209
+_ve	 208
+ris	 208
+esti	 208
+!_	 207
+men	 206
+vas	 205
+iel	 204
+taj	 203
+_c	 201
+aro	 201
+ank	 200
+_pri	 200
+jo	 200
+ja	 200
+ont	 200
+lt	 199
+_P	 199
+igi	 199
+_pa	 197
+oj.	 197
+(	 196
+au	 195
+oro	 195
+ng	 195
+_(	 194
+sto	 194
+ast	 194
+ag	 193
diff --git a/libtextcat/data/new_fingerprints/lm/estonian.lm b/libtextcat/data/new_fingerprints/lm/estonian.lm
new file mode 100644
index 000000000000..74a7aa014324
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/estonian.lm
@@ -0,0 +1,400 @@
+_	 20738
+a	 7004
+e	 5699
+i	 5321
+s	 4731
+t	 3769
+l	 3448
+u	 3446
+n	 2902
+k	 2584
+d	 2202
+m	 2043
+a_	 1758
+o	 1684
+r	 1429
+g	 1174
+v	 1151
+e_	 1139
+i_	 1136
+_k	 1136
+s_	 1077
+h	 1009
+,	 995
+,_	 995
+_t	 953
+p	 953
+j	 940
+ä	 900
+is	 896
+st	 851
+se	 841
+_s	 822
+.	 821
+as	 801
+d_	 801
+le	 800
+ta	 794
+in	 793
+_m	 790
+ô	 754
+._	 753
+t_	 746
+ma	 710
+_p	 680
+si	 677
+_v	 660
+es	 636
+al	 626
+us	 619
+el	 602
+_o	 596
+_e	 586
+ja	 580
+_j	 563
+te	 562
+ü	 549
+li	 532
+va	 515
+id	 501
+ol	 498
+tu	 497
+da	 490
+_n	 480
+ku	 478
+ud	 459
+nu	 455
+na	 438
+ei	 432
+ks	 418
+mi	 411
+ee	 411
+u_	 407
+ka	 400
+n_	 394
+b	 394
+ga	 386
+_l	 384
+_a	 380
+an	 366
+ja_	 365
+et	 358
+me	 358
+l_	 350
+at	 348
+la	 341
+ad	 340
+st_	 339
+ne	 336
+ll	 333
+_ta	 332
+ra	 330
+_ja	 328
+ik	 323
+en	 318
+ni	 308
+ul	 305
+sa	 302
+_ol	 302
+nd	 299
+_ja_	 299
+nud	 296
+ii	 291
+ko	 286
+_se	 285
+le_	 283
+aa	 281
+is_	 281
+gi	 270
+_te	 269
+ag	 269
+_va	 268
+_ku	 267
+ed	 262
+em	 255
+_mi	 255
+ma_	 247
+ti	 246
+ri	 245
+_h	 242
+gu	 239
+id_	 238
+ast	 237
+it	 236
+ga_	 236
+un	 232
+de	 230
+ud_	 230
+ha	 230
+ak	 228
+ah	 228
+uu	 228
+il	 227
+ôi	 226
+as_	 223
+ke	 222
+ar	 220
+a,	 220
+am	 220
+_ko	 220
+a,_	 220
+_ka	 220
+ai	 220
+eg	 216
+sin	 214
+est	 214
+ui	 214
+he	 214
+ks_	 213
+ö	 213
+oo	 213
+ju	 207
+är	 205
+ut	 203
+in_	 203
+oli	 201
+ki	 199
+su	 199
+es_	 199
+lt	 198
+ist	 188
+li_	 186
+ea	 186
+vi	 184
+im	 181
+mu	 181
+se_	 180
+ts	 180
+on	 178
+ise	 178
+ta_	 177
+ek	 176
+_oli	 176
+sel	 173
+nud_	 173
+_ü	 172
+a.	 171
+nn	 170
+ema	 169
+ng	 168
+lu	 168
+ge	 167
+_si	 166
+_ei	 165
+_i	 165
+_ei_	 164
+ei_	 164
+_r	 163
+ole	 161
+pa	 160
+lle	 160
+a._	 160
+ust	 159
+du	 156
+er	 156
+vô	 153
+da_	 153
+min	 152
+et_	 151
+d,_	 149
+_M	 149
+ht	 149
+d,	 149
+M	 149
+kui	 148
+_et	 147
+K	 147
+_K	 146
+pe	 145
+gi_	 145
+_vô	 145
+or	 144
+_tu	 142
+lt_	 141
+_ma	 141
+asi	 140
+ve	 139
+us_	 138
+ig	 136
+sin_	 136
+ur	 135
+_ta_	 134
+di	 134
+_et_	 134
+s,_	 132
+tas	 132
+s,	 132
+_kui	 131
+sk	 131
+re	 130
+po	 129
+oli_	 129
+om	 129
+äi	 128
+inu	 128
+_na	 128
+_oli_	 128
+_sa	 128
+aj	 128
+mis	 127
+ui_	 127
+_me	 127
+_pa	 126
+tus	 125
+pi	 125
+te_	 124
+ül	 123
+-	 123
+est_	 122
+_on	 121
+kk	 121
+tt	 120
+aga	 119
+na_	 119
+_T	 119
+T	 119
+b_	 118
+al_	 118
+sta	 118
+_mu	 116
+_ju	 116
+ida	 116
+aks	 116
+gu_	 116
+_ni	 116
+s.	 116
+ad_	 116
+_pe	 114
+eks	 114
+ev	 114
+end	 113
+s._	 113
+use	 111
+ära	 111
+_po	 111
+_min	 110
+S	 110
+aja	 110
+_la	 110
+ele	 109
+el_	 108
+on_	 108
+ab	 108
+_S	 108
+av	 107
+ing	 107
+kui_	 106
+_on_	 106
+au	 104
+ne_	 104
+ti_	 104
+ell	 103
+ae	 101
+kô	 101
+ed_	 100
+_ke	 99
+ata	 99
+iis	 99
+!	 98
+!_	 98
+sid	 98
+nda	 98
+eh	 98
+lle_	 97
+pu	 97
+ää	 97
+vôi	 97
+ine	 96
+t,	 96
+e,_	 96
+ale	 96
+_vôi	 96
+t,_	 96
+e,	 96
+eda	 96
+uk	 95
+ast_	 95
+ld	 95
+?	 94
+_kui_	 94
+_sel	 93
+_kô	 93
+tul	 93
+ega	 93
+lg	 92
+sii	 92
+val	 92
+e.	 92
+_su	 92
+ug	 92
+oh	 92
+kü	 92
+d.	 91
+ee_	 91
+see	 91
+e._	 91
+öö	 91
+oma	 91
+_ole	 90
+ses	 90
+stu	 90
+ôt	 90
+üü	 90
+_om	 89
+me_	 89
+ot	 89
+d._	 89
+_sii	 88
+to	 88
+_en	 87
+atu	 87
+?_	 87
+A	 86
+J	 86
+pea	 86
+jä	 85
+_A	 85
+_see	 85
+ime	 84
+_pi	 84
+_ha	 84
+mô	 84
+nä	 84
+_J	 84
+les	 84
+ste	 84
+kas	 84
+_ä	 84
+vä	 83
+E	 83
+pä	 83
+_ve	 83
+_E	 83
+eis	 82
+_jä	 81
+_pea	 81
+_mô	 80
+um	 80
+_kü	 80
+iku	 80
+üd	 80
+all	 79
+eid	 79
+ba	 79
+_vä	 79
+ina	 78
+lj	 78
+sid_	 78
+hu	 78
+tun	 78
+lä	 78
+_oma	 77
+i,_	 77
+i,	 77
+agu	 77
+uh	 77
+lm	 76
+ras	 76
+ss	 76
+kä	 76
+ees	 76
diff --git a/libtextcat/data/new_fingerprints/lm/finnish.lm b/libtextcat/data/new_fingerprints/lm/finnish.lm
new file mode 100644
index 000000000000..328f88604279
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/finnish.lm
@@ -0,0 +1,400 @@
+_	 19984
+a	 9133
+i	 8384
+t	 7797
+e	 6481
+n	 6431
+s	 5897
+l	 4504
+o	 4163
+u	 4106
+k	 4013
+ä	 3354
+n_	 2868
+m	 2569
+a_	 1987
+v	 1905
+r	 1827
+ta	 1580
+en	 1553
+is	 1515
+h	 1508
+y	 1462
+st	 1390
+in	 1375
+p	 1342
+j	 1333
+an	 1139
+si	 1073
+tt	 1030
+te	 1008
+en_	 982
+_k	 980
+it	 974
+ll	 947
+aa	 942
+ä_	 902
+va	 878
+el	 855
+_t	 851
+ka	 846
+i_	 835
+.	 832
+se	 818
+li	 806
+tä	 804
+oi	 767
+ai	 744
+._	 739
+tu	 734
+_o	 719
+mi	 715
+al	 703
+on	 684
+d	 681
+_v	 662
+et	 654
+_j	 641
+t_	 635
+ti	 632
+_m	 628
+_s	 620
+ja	 616
+ma	 596
+sa	 595
+la	 582
+ist	 575
+_e	 565
+to	 565
+ks	 557
+in_	 554
+es	 551
+il	 538
+an_	 536
+ki	 527
+,	 525
+ku	 525
+,_	 524
+us	 520
+as	 514
+nt	 512
+ri	 495
+ke	 494
+at	 491
+_p	 485
+le	 484
+ik	 483
+ss	 477
+ut	 469
+ö	 469
+sta	 460
+ee	 459
+uu	 458
+ol	 457
+ta_	 451
+ne	 445
+ää	 445
+ei	 443
+uo	 436
+ko	 433
+un	 430
+lu	 421
+ii	 420
+e_	 418
+nn	 413
+_h	 412
+ar	 408
+er	 402
+än	 396
+ja_	 386
+im	 381
+on_	 365
+_va	 363
+aan	 354
+_a	 352
+me	 350
+ak	 345
+ssa	 331
+na	 330
+ie	 329
+pa	 327
+_ja	 326
+ia	 325
+tä_	 322
+_l	 319
+vi	 317
+ise	 316
+tta	 315
+de	 314
+os	 312
+lli	 309
+_ja_	 304
+jo	 295
+vä	 290
+su	 289
+au	 287
+lis	 286
+_on	 285
+sä	 284
+uk	 280
+am	 280
+ot	 280
+ty	 275
+ett	 271
+ttä	 270
+ni	 269
+lä	 267
+ksi	 264
+nk	 264
+ht	 263
+ul	 261
+ell	 261
+sa_	 259
+ha	 257
+sen	 257
+a.	 254
+isi	 253
+ste	 253
+aan_	 252
+_on_	 252
+_ka	 252
+sk	 251
+kk	 246
+itt	 245
+ok	 242
+a._	 239
+all	 239
+yt	 239
+mä	 237
+mu	 237
+av	 237
+_y	 236
+lla	 233
+taa	 231
+ais	 231
+een	 230
+K	 230
+lt	 228
+s_	 227
+ast	 227
+iv	 226
+ssa_	 225
+ra	 225
+-	 223
+kse	 223
+oit	 220
+om	 220
+T	 219
+_ku	 218
+än_	 216
+aa_	 214
+at_	 214
+tel	 211
+ui	 210
+si_	 208
+rk	 207
+sta_	 207
+_jo	 203
+kä	 202
+_K	 201
+est	 200
+em	 200
+he	 199
+_n	 199
+vo	 198
+_ta	 196
+eh	 196
+_ol	 196
+S	 196
+nta	 196
+_ko	 194
+je	 194
+stä	 194
+är	 193
+ust	 191
+mis	 191
+ns	 190
+pu	 189
+nen	 188
+ät	 188
+toi	 188
+iin	 187
+ten	 187
+min	 186
+ista	 185
+hd	 184
+a,	 184
+a,_	 184
+sen_	 183
+E	 182
+lle	 181
+vat	 179
+ill	 177
+no	 176
+pä	 176
+lm	 176
+llis	 175
+n.	 175
+io	 172
+ine	 171
+n._	 170
+pi	 169
+uks	 168
+ava	 168
+ään	 166
+nen_	 165
+ah	 165
+_mu	 164
+tus	 163
+mm	 162
+_to	 162
+ek	 160
+int	 159
+_r	 159
+lin	 158
+oim	 158
+_T	 158
+A	 158
+imi	 157
+tö	 157
+la_	 157
+jä	 157
+aj	 156
+yh	 155
+o_	 154
+lo	 154
+oli	 153
+een_	 153
+le_	 153
+_si	 153
+g	 152
+aik	 151
+vat_	 150
+L	 149
+ur	 149
+ti_	 149
+sia	 148
+ite	 147
+inen	 147
+ain	 146
+sti	 146
+lla_	 146
+ys	 145
+_mi	 145
+val	 144
+stu	 144
+äm	 144
+alli	 143
+pe	 143
+utt	 142
+et_	 141
+_tu	 141
+eri	 140
+_E	 140
+:	 140
+nki	 139
+ir	 139
+llä	 138
+up	 138
+äi	 137
+ama	 137
+_ha	 135
+id	 135
+_se	 135
+po	 134
+inen_	 134
+tte	 133
+nna	 133
+ten_	 132
+or	 132
+ts	 131
+nä	 131
+yk	 131
+äs	 131
+_S	 130
+ses	 130
+ve	 130
+ess	 129
+äl	 129
+ita	 129
+lai	 129
+H	 129
+van	 127
+äk	 127
+kin	 127
+N	 127
+_te	 126
+den	 126
+tee	 126
+P	 126
+kaa	 126
+iin_	 125
+kun	 125
+ois	 125
+sit	 125
+oh	 124
+V	 124
+yö	 124
+äv	 124
+tav	 124
+voi	 124
+ia_	 123
+I	 123
+oll	 123
+maa	 122
+ih	 122
+oj	 122
+rj	 121
+ro	 121
+ikk	 120
+so	 120
+oo	 120
+oimi	 120
+do	 120
+pp	 119
+M	 119
+_ei	 118
+toim	 118
+op	 118
+uut	 118
+tet	 118
+_i	 118
+_ma	 117
+vai	 117
+lä_	 116
+u_	 116
+sy	 116
+kau	 116
+utta	 116
+un_	 115
+eu	 115
+ssä	 115
+tti	 115
+_sa	 115
+mp	 114
+eis	 114
+ka_	 112
+että	 112
+taa_	 111
+_et	 111
+hu	 111
+itu	 111
+suu	 111
+den_	 111
+ksen	 110
+ap	 110
+_ke	 110
+uv	 110
+tam	 110
+yv	 109
+aup	 109
+stä_	 109
+asta	 109
+äy	 109
+kan	 108
+nu	 108
+ukse	 108
+_toi	 107
+ien	 107
+hi	 107
+iss	 107
diff --git a/libtextcat/data/new_fingerprints/lm/french.lm b/libtextcat/data/new_fingerprints/lm/french.lm
new file mode 100644
index 000000000000..5080d9cba9d5
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/french.lm
@@ -0,0 +1,400 @@
+_	 20800
+e	 7258
+i	 4051
+s	 4003
+a	 3972
+n	 3903
+r	 3650
+t	 3590
+u	 2968
+o	 2823
+l	 2723
+e_	 2632
+d	 2241
+s_	 1721
+_d	 1693
+c	 1663
+p	 1528
+é	 1320
+m	 1297
+es	 1164
+t_	 1106
+_l	 1079
+de	 1048
+on	 959
+_de	 940
+en	 939
+_p	 852
+nt	 825
+le	 808
+es_	 791
+re	 777
+,	 721
+,_	 720
+n_	 703
+de_	 685
+'	 670
+an	 667
+_de_	 645
+v	 641
+_s	 610
+r_	 596
+_c	 594
+er	 585
+ai	 575
+_a	 558
+_e	 554
+ou	 554
+q	 549
+qu	 538
+is	 530
+te	 528
+ti	 525
+ur	 519
+it	 514
+g	 498
+a_	 490
+f	 480
+la	 476
+in	 475
+_le	 441
+me	 436
+nt_	 432
+.	 427
+b	 427
+ra	 423
+io	 416
+ent	 415
+._	 404
+ne	 395
+ns	 392
+ion	 383
+h	 381
+ue	 376
+se	 371
+le_	 370
+ar	 370
+ie	 362
+co	 361
+at	 359
+tr	 359
+et	 349
+pr	 342
+ce	 336
+au	 328
+u_	 321
+il	 314
+_r	 313
+_la	 304
+un	 303
+eu	 303
+st	 300
+re_	 296
+ro	 290
+la_	 288
+on_	 287
+_m	 286
+_la_	 283
+que	 281
+_qu	 280
+_q	 280
+po	 275
+tio	 273
+tion	 273
+pa	 273
+li	 271
+_t	 269
+nc	 268
+si	 266
+_pr	 265
+ri	 264
+al	 263
+ui	 262
+_co	 259
+i_	 255
+ta	 255
+é_	 251
+x	 247
+em	 244
+l_	 243
+et_	 238
+_l'	 236
+l'	 236
+les	 233
+ns_	 233
+ir	 232
+_le_	 228
+ent_	 227
+or	 226
+ré	 224
+_f	 224
+ne_	 222
+à	 221
+ve	 220
+ch	 220
+it_	 219
+di	 219
+oi	 217
+-	 216
+ni	 215
+à_	 215
+les_	 215
+d'	 214
+el	 212
+ss	 212
+_n	 212
+ut	 211
+our	 210
+des	 210
+"	 208
+ur_	 207
+nd	 207
+er_	 206
+ait	 206
+ion_	 204
+rs	 202
+_en	 201
+_et	 200
+j	 200
+_d'	 200
+ll	 199
+_des	 198
+des_	 197
+_pa	 197
+té	 196
+_et_	 195
+_à	 195
+_à_	 195
+om	 193
+ma	 192
+ati	 190
+_des_	 189
+L	 188
+so	 187
+_u	 185
+è	 184
+_"	 183
+sa	 182
+_po	 181
+tre	 181
+dé	 181
+ue_	 180
+pe	 179
+en_	 179
+ont	 178
+_un	 178
+_L	 178
+us	 176
+_les	 176
+_les_	 176
+rt	 176
+is_	 173
+_i	 173
+du	 172
+e,_	 171
+e,	 171
+na	 171
+s,	 170
+s,_	 170
+as	 169
+men	 169
+M	 167
+ait_	 167
+'a	 166
+vi	 162
+ci	 159
+ant	 158
+_au	 158
+da	 157
+_M	 157
+ation	 155
+atio	 155
+con	 154
+que_	 153
+ons	 153
+eur	 151
+est	 149
+me_	 149
+mi	 149
+par	 148
+tion_	 148
+_so	 147
+te_	 147
+res	 144
+lo	 144
+ment	 144
+és	 144
+ans	 143
+_du	 142
+du_	 141
+ux	 141
+un_	 140
+y	 138
+pro	 138
+_du_	 136
+_dé	 136
+ce_	 135
+_se	 134
+_re	 134
+pl	 133
+A	 132
+ge	 131
+ic	 131
+su	 130
+x_	 129
+ien	 129
+nce	 129
+"_	 129
+ac	 128
+il_	 128
+qui	 128
+_pro	 127
+no	 127
+av	 126
+_v	 125
+_o	 125
+rs_	 125
+ans_	 124
+eme	 124
+bl	 123
+emen	 122
+_en_	 122
+iqu	 122
+ct	 122
+iq	 122
+lle	 122
+nn	 121
+ts	 121
+ement	 121
+ét	 120
+_"_	 120
+ér	 119
+té_	 119
+_ce	 119
+mp	 119
+ire	 119
+ui_	 119
+to	 118
+he	 117
+_é	 117
+ca	 117
+_j	 116
+ec	 116
+va	 116
+_par	 116
+ée	 115
+_con	 115
+se_	 114
+tre_	 113
+ique	 112
+dan	 111
+éc	 111
+ha	 110
+une	 110
+P	 110
+lu	 110
+ux_	 109
+_b	 108
+s.	 108
+pou	 108
+_pou	 108
+ier	 107
+C	 107
+ais	 106
+s._	 105
+ain	 104
+_un_	 104
+nte	 103
+'e	 103
+mo	 103
+mm	 103
+ment_	 102
+une_	 102
+com	 101
+_P	 101
+'i	 101
+_ma	 100
+do	 99
+ant_	 98
+anc	 98
+che	 97
+ap	 97
+ont_	 97
+_que	 97
+os	 97
+urs	 96
+_di	 96
+fi	 96
+im	 96
+pour	 96
+_pour	 96
+ê	 95
+ts_	 95
+_g	 95
+our_	 94
+_sa	 94
+ntr	 94
+_da	 94
+_ré	 93
+rai	 93
+rm	 93
+_qui	 93
+e.	 92
+am	 92
+_com	 91
+uv	 91
+_C	 91
+D	 91
+qui_	 90
+e._	 90
+pu	 89
+_qui_	 88
+ia	 87
+_dan	 87
+_dans	 87
+dans	 87
+ter	 87
+fo	 87
+son	 87
+dans_	 87
+id	 86
+ag	 86
+ine	 86
+tu	 85
+ran	 85
+au_	 85
+ol	 85
+oc	 84
+est_	 84
+st_	 84
+enc	 84
+F	 82
+_tr	 81
+'u	 81
+tai	 81
+ell	 80
+R	 79
+_su	 79
+S	 79
+ions	 79
+pré	 79
+sé	 78
+ab	 78
+né	 77
+_que_	 77
+_in	 77
+_av	 76
+pour_	 76
+fa	 76
+rr	 76
+air	 75
+_ch	 75
+_a_	 75
+ba	 74
+_pl	 74
+gr	 74
+tt	 74
+ssi	 74
+rd	 73
+pas	 73
+bi	 73
diff --git a/libtextcat/data/new_fingerprints/lm/frisian.lm b/libtextcat/data/new_fingerprints/lm/frisian.lm
new file mode 100644
index 000000000000..9efa35f370c8
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/frisian.lm
@@ -0,0 +1,400 @@
+_	 46446
+e	 15767
+n	 9616
+i	 7837
+a	 7830
+t	 7562
+r	 7297
+s	 6307
+o	 4784
+n_	 4595
+d	 4564
+e_	 4213
+l	 4032
+k	 3951
+t_	 3079
+en	 2863
+m	 2605
+er	 2492
+y	 2462
+f	 2371
+_d	 2253
+de	 2124
+h	 1943
+in	 1899
+w	 1898
+en_	 1857
+_i	 1815
+u	 1769
+g	 1738
+an	 1690
+j	 1678
+p	 1651
+r_	 1619
+_f	 1602
+.	 1601
+ar	 1561
+te	 1545
+b	 1488
+s_	 1476
+._	 1435
+_s	 1370
+de_	 1235
+_de	 1224
+_w	 1181
+it	 1172
+ie	 1140
+,	 1078
+_o	 1056
+,_	 1056
+oa	 1045
+_e	 1040
+st	 1038
+an_	 1010
+_b	 972
+_de_	 965
+ke	 949
+_m	 947
+_t	 933
+ne	 920
+er_	 895
+at	 863
+sk	 856
+c	 850
+it_	 848
+_h	 838
+ei	 832
+k_	 817
+yn	 790
+ch	 784
+le	 772
+is	 769
+je	 765
+el	 761
+me	 758
+ea	 754
+_k	 740
+fa	 736
+in_	 735
+'	 733
+_it	 733
+_it_	 727
+ge	 727
+re	 725
+al	 724
+_fa	 684
+yn_	 640
+aa	 628
+fan	 626
+_y	 618
+ar_	 617
+et	 616
+ri	 615
+_fan	 613
+_n	 612
+li	 611
+_yn	 610
+_en	 598
+fan_	 594
+oe	 589
+_fan_	 584
+_en_	 583
+at_	 581
+_in	 570
+oar	 565
+_in_	 560
+y_	 555
+F	 549
+es	 540
+_a	 536
+ng	 523
+be	 514
+sj	 512
+nt	 510
+l_	 510
+_F	 506
+ns	 506
+D	 499
+te_	 499
+der	 497
+_yn_	 497
+ti	 493
+ek	 490
+ro	 476
+rs	 474
+rd	 473
+se	 470
+fo	 470
+ys	 462
+op	 461
+û	 461
+we	 456
+ry	 451
+da	 445
+d_	 443
+is_	 442
+_D	 440
+ur	 433
+i_	 432
+ha	 426
+_me	 425
+ear	 422
+_l	 417
+ed	 410
+as	 409
+om	 407
+ei_	 406
+Fr	 405
+nd	 404
+_fo	 394
+_p	 393
+oc	 390
+rys	 389
+ol	 386
+_Fr	 386
+och	 383
+fe	 381
+ik	 379
+ma	 379
+ra	 377
+nn	 374
+_g	 368
+_da	 367
+di	 363
+ts	 362
+ta	 361
+a_	 360
+ko	 359
+et_	 358
+ysk	 356
+Fry	 354
+Frys	 354
+z	 354
+ll	 350
+_be	 349
+ke_	 348
+I	 347
+ing	 346
+_'	 345
+m_	 343
+h_	 340
+ske	 339
+_ha	 338
+sje	 336
+_Fry	 336
+_Frys	 336
+wi	 335
+_op	 334
+p_	 334
+_is	 333
+ch_	 333
+tr	 330
+ten	 328
+ers	 327
+wa	 325
+ter	 322
+ji	 322
+rysk	 319
+_ne	 319
+je_	 312
+foa	 311
+ê	 309
+jo	 307
+_is_	 307
+ste	 307
+_te	 306
+â	 301
+n.	 301
+nne	 300
+rt	 300
+foar	 299
+S	 299
+mei	 299
+_r	 298
+_oa	 297
+wu	 293
+ak	 291
+si	 290
+wur	 290
+ni	 290
+pe	 288
+Frysk	 287
+oan	 286
+n._	 285
+_mei	 284
+der_	 281
+_foar	 281
+_foa	 281
+ht	 278
+cht	 277
+-	 275
+ú	 275
+_j	 274
+ne_	 273
+ken	 273
+fer	 271
+ûn	 270
+am	 270
+on	 268
+nde	 264
+_S	 264
+B	 262
+ki	 261
+id	 261
+le_	 261
+dat	 260
+v	 259
+_I	 256
+oar_	 255
+op_	 254
+lle	 252
+la	 244
+tt	 243
+dat_	 242
+_fe	 242
+mm	 240
+inn	 239
+_wi	 239
+_dat	 237
+g_	 236
+mei_	 236
+al_	 235
+_B	 234
+e.	 234
+ld	 231
+_al	 230
+_wur	 230
+urd	 230
+_wu	 230
+_op_	 230
+De	 229
+inne	 228
+ng_	 227
+_mei_	 227
+'t	 226
+ks	 226
+'t_	 224
+_dat_	 224
+_ko	 223
+_st	 220
+ân	 219
+rk	 219
+sa	 219
+e._	 219
+tte	 218
+en.	 218
+n,	 217
+ier	 216
+ten_	 216
+_fer	 215
+mi	 215
+hi	 215
+ien	 214
+_wa	 213
+n,_	 213
+no	 213
+_te_	 212
+ig	 212
+_De	 212
+ske_	 212
+_der	 212
+W	 211
+H	 211
+_oan	 210
+ee	 209
+dy	 208
+ek_	 207
+en._	 207
+ic	 207
+mme	 206
+yk	 204
+pr	 204
+net	 203
+foar_	 203
+he	 203
+wurd	 201
+_der_	 199
+jen	 199
+_dy	 199
+kr	 198
+ka	 197
+im	 196
+_H	 196
+il	 196
+ze	 196
+_ma	 195
+by	 194
+oer	 194
+kt	 193
+us	 193
+M	 193
+sk_	 192
+wo	 192
+_hi	 191
+or	 190
+ing_	 190
+_W	 190
+ich	 189
+De_	 187
+rr	 186
+int	 185
+_ú	 184
+:	 184
+ij	 184
+_ek	 183
+eg	 182
+:_	 180
+gen	 180
+as_	 180
+_se	 179
+e,	 178
+_net	 177
+e,_	 177
+ins	 177
+N	 177
+ls	 176
+st_	 176
+_wurd	 176
+ie_	 175
+E	 175
+nne_	 175
+_De_	 175
+sy	 175
+wer	 174
+gr	 174
+f_	 173
+nk	 172
+och_	 172
+net_	 169
+ad	 169
+_we	 169
+rde	 168
+sl	 168
+bi	 168
+of	 168
+so	 168
+_no	 167
+_ta	 167
+re_	 167
+to	 167
+den	 167
+J	 167
+t.	 166
+It	 165
+út	 165
+inne_	 165
+ysk_	 165
+lik	 164
+sp	 163
+_ek_	 162
+ou	 162
+tsj	 162
+It_	 161
+_sa	 160
+A	 160
+wol	 160
+lâ	 159
+_wo	 159
+ge_	 159
+lân	 159
+ige	 158
diff --git a/libtextcat/data/new_fingerprints/lm/georgian.lm b/libtextcat/data/new_fingerprints/lm/georgian.lm
new file mode 100644
index 000000000000..0e88ab08a895
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/georgian.lm
@@ -0,0 +1,400 @@
+_	 14926
+À	 7221
+È	 5780
+Ä	 4137
+Ð	 2966
+Ñ	 2908
+Ë	 2607
+Ê	 2372
+Í	 2260
+Å	 2080
+Ã	 2078
+Ì	 2005
+Ç	 1598
+Á	 1383
+Ó	 1363
+È_	 1248
+À_	 1149
+Â	 1145
+ÊÈ	 1009
+Þ	 974
+_Ë	 965
+Ñ_	 964
+ÃÀ	 912
+ÈÑ	 901
+ÀÐ	 897
+Ø	 820
+.	 813
+ÄÁ	 767
+"	 762
+._	 735
+,	 720
+,_	 718
+ÑÀ	 684
+_À	 669
+Ú	 653
+ËÀ	 631
+ÀÌ	 622
+ÄÊ	 575
+ÐÈ	 570
+ÅÄ	 567
+Õ	 551
+_Ã	 550
+Ò	 542
+_Ñ	 526
+É	 518
+ÀË	 517
+ÅÀ	 485
+ÅÈ	 479
+ÂÀ	 478
+_Â	 474
+ÓÊ	 468
+_È	 436
+ÐÀ	 435
+ÀÅ	 420
+ËÈ	 419
+ÌÈ	 418
+ÄÐ	 416
+ÄÌ	 412
+ÈÑ_	 407
+_ÃÀ	 404
+ÃÀ_	 393
+ÀÊ	 384
+ËÍ	 382
+Ü	 376
+_"	 374
+ÊÈ_	 371
+×	 369
+ÐÍ	 364
+ÀÑ	 360
+ÈÇ	 358
+ÀÃ	 353
+ÌÀ	 349
+Ô	 349
+ÁÀ	 342
+Æ	 341
+ËÄ	 335
+ÈÀ	 334
+ÈÊ	 332
+ÐÇ	 326
+_Ð	 322
+ÁÈ	 321
+ØÈ	 319
+_Ä	 319
+_Ø	 319
+ÃÄ	 317
+_ÂÀ	 316
+ÇÀ	 316
+ÄÑ	 306
+Ä_	 299
+_Ç	 288
+ÐÄ	 279
+ÓÊÈ	 273
+ÊÍ	 271
+Ö	 270
+Ì_	 267
+ÌÄ	 267
+_ÑÀ	 266
+ÍÁ	 263
+ÓÐ	 260
+Ç_	 256
+ÄÊÈ	 255
+ÃÈ	 238
+ÊÄ	 238
+ÑÈ	 234
+ÊÀ	 233
+ÍÐ	 230
+ÈÌ	 229
+_Þ	 227
+"_	 225
+ÄÁÈ	 224
+:	 224
+:_	 223
+È.	 221
+_ÃÀ_	 217
+Û	 215
+ÞÄ	 213
+È,	 213
+È,_	 212
+_Ó	 211
+Í_	 209
+_ËÀ	 208
+ÈÑÀ	 208
+ÍË	 206
+_ÀÐ	 204
+ÇÅ	 203
+ÀÐÇ	 203
+ØÄ	 203
+È._	 201
+À.	 200
+-	 193
+ÀÞ	 192
+ÅÄÊ	 192
+Ú_	 189
+ÈÃ	 188
+Ù	 188
+ÕÀ	 187
+Ã_	 185
+ÈÊÈ	 183
+ÄÃ	 179
+À._	 177
+Ð_	 177
+ÍÃ	 174
+ÞÀ	 174
+ÈÐ	 173
+ÌÃ	 172
+_ÐÍ	 172
+ÍÑ	 172
+ÄÁÀ	 171
+_ËÍ	 170
+ÐÈ_	 170
+_ËÈ	 170
+_Ü	 169
+ÇÈ	 166
+ÁÄ	 166
+_Õ	 165
+ØÈ_	 165
+ÄÑ_	 163
+ÀÈ	 162
+_ØÄ	 160
+ÄÅ	 158
+_É	 155
+ÀÚ	 154
+ÊÈÑ	 153
+Î	 151
+Ë_	 149
+ÕÀÐ	 148
+À,_	 147
+À,	 147
+ÀÇ	 147
+ÀÂ	 145
+ÕÀÐÇ	 145
+ÈÂ	 143
+ËÀÐ	 143
+ÍÊ	 143
+ÀÊÈ	 142
+ÂÈ	 142
+ÌÄÁ	 141
+ÄË	 140
+ÀØ	 139
+ÓÊÈ_	 139
+ÄÇ	 139
+ÇÓ	 138
+_Ì	 136
+ÈÇ_	 135
+ÀÐÈ	 133
+ÀÌ_	 132
+ÊÄÁ	 131
+×Í	 130
+ÑÄ	 130
+ÈË	 130
+ÐÄÁ	 128
+ÀÕ	 125
+ÆÄ	 125
+ÔÄ	 125
+Ê_	 124
+ÀÅÈ	 124
+ÀÃ_	 124
+ÅÈÑ	 123
+_ËÄ	 123
+ÀËÈ	 122
+_ÕÀ	 121
+ÉÈ	 121
+_Å	 120
+×Å	 120
+ÍÅ	 116
+_Á	 114
+ÀÌÈ	 113
+ÀËÍ	 113
+ÂÀÌ	 113
+ÍÌ	 112
+ÉÀ	 112
+ÈÚ	 112
+ØÀ	 112
+ÀÐÀ	 111
+ÁÓ	 111
+ÞÅ	 109
+ÀÖ	 109
+ÂÍ	 107
+ÁÀ_	 107
+ÌÈ_	 107
+ÅÀÐ	 107
+ÄÊÈ_	 106
+ÐÃ	 106
+ÀÐ_	 106
+_ÀË	 105
+ß	 104
+ÄÐÇ	 104
+_ÄÐ	 104
+ÅÄÌ	 103
+_ÄÑ	 103
+ÐÍË	 103
+ÄÌÈ	 103
+_Ú	 103
+ÁÍ	 102
+_Ù	 102
+ËÈÑ	 102
+ÐÈÑ	 102
+ÞÍ	 102
+_ÐÍË	 101
+_ÕÀÐ	 101
+ÈÅ	 100
+_ÕÀÐÇ	 100
+ÓÐÈ	 99
+ÒÈ	 99
+ÂÄ	 99
+ÈÒ	 99
+ÀÀ	 97
+ÀÒ	 97
+ÁÓÊ	 96
+ÕÅ	 94
+ÈÄ	 94
+_ÇÀ	 94
+Ñ,_	 93
+ÐÑ	 93
+ÅÊ	 93
+_ØÀ	 93
+Ñ,	 93
+_ÑÈ	 93
+ÀÉ	 93
+ÀÆ	 92
+ÍÁÀ	 92
+ÀÑ_	 92
+ÌÍ	 91
+ÄÁÓ	 91
+ÇÕ	 91
+ËÓ	 90
+ÄÌ_	 90
+ÇÀÅ	 89
+ÄÁÓÊ	 89
+ÊÑ	 89
+ÀØÈ	 89
+ÃÄÁ	 89
+ÀÁ	 89
+È"	 89
+Ñ.	 88
+ÚÞ	 88
+ÂÀË	 88
+ÍÑ_	 87
+_ÄÐÇ	 87
+È×	 87
+ÁÈÑ	 87
+ÌÃÀ	 87
+ØÅ	 87
+ÞÄÊ	 87
+ÁÈÇ	 85
+ÑÀ_	 85
+ÇÅÄ	 85
+ÓÌ	 85
+ÒÀ	 85
+_Î	 84
+ÊÈ.	 84
+_ÐÀ	 83
+Ñ._	 83
+_Ô	 83
+_ÂÀË	 83
+ÊÈÀ	 83
+ÊÈ._	 82
+ÄÐÈ	 82
+ÈÀ_	 82
+ÈÀÌ	 82
+ÜÈ	 81
+ÀÚ_	 81
+"Ë	 81
+ÈÓ	 80
+_"Ë	 80
+ÐÇÅ	 80
+_ÄÑ_	 79
+_ÈÂ	 79
+ÀÓ	 79
+ÈÕ	 79
+ÀÐÇÅ	 79
+ÇÈ_	 79
+ÑÀÞ	 79
+ÐÇÓ	 78
+ÊÈ,	 78
+ÚÈ	 78
+ÞÈ	 78
+ÐÇÓÊ	 78
+ÇÓÊ	 78
+ÊÈ,_	 78
+ÀÃÀ	 78
+ÁÑ	 78
+_ÀÐ_	 77
+ÞÊ	 77
+ÐÓ	 77
+ÀÐÇÓÊ	 77
+_ÌÀ	 77
+ÅÈÇ	 77
+ÈÂÈ	 77
+ÀÐÇÓ	 77
+ÜÀ	 76
+ÅÀ_	 75
+_ÞÀ	 75
+ÉÅ	 75
+ÒÄ	 75
+ÐÀ_	 75
+ÅÀÊ	 75
+ÇÅÄÊ	 74
+ÐÇÅÄ	 74
+ÀÐÇÅÄ	 74
+ÄÁÀ_	 74
+ÐË	 73
+ÑÞ	 73
+ÑÒ	 73
+ÅÑ	 73
+ÑÓ	 73
+ÐÇÅÄÊ	 73
+ËÞ	 73
+ÍÊÍ	 72
+ÐÚ	 72
+_×	 72
+ÂÐ	 71
+ÅÄ_	 71
+ÒÍ	 71
+ÇÄ	 71
+ÍÂ	 71
+ÅÄÁ	 71
+ÕÀÐÇÓ	 71
+ÐÀÃ	 70
+ÀË_	 70
+ÅÃ	 69
+ËÀ_	 69
+ÍÄ	 69
+_ÀÐÀ	 67
+à	 67
+ÄÃÀ	 67
+ÇÀÌ	 67
+È×Í	 67
+ÕÀÐÇÅ	 67
+Ò×	 67
+ÂÀËÍ	 66
+_ÂÀËÍ	 66
+ÄÒ	 66
+ÍÃÀ	 66
+ÅÄÊÈ	 66
+ÀÌÀ	 66
+ÄÁÈÇ	 66
+_ÈÂÈ	 66
+ÄÊÍ	 65
+ÄÂ	 65
+ËÈÊ	 65
+ÊË	 65
+ÈÊÈ_	 65
+ÍÁÈ	 65
+ÅÐ	 65
+_ÈÑ	 64
+Ó_	 63
+ËÃ	 63
+",	 63
+ÃÍ	 63
+ÊÍÁ	 63
+ÂÅ	 63
+ÃÂ	 63
+ÄÍ	 62
+À"	 62
+ÀÅÀ	 62
+?	 62
+",_	 62
+!	 62
+_È×	 62
diff --git a/libtextcat/data/new_fingerprints/lm/german.lm b/libtextcat/data/new_fingerprints/lm/german.lm
new file mode 100644
index 000000000000..eb4eda0f8239
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/german.lm
@@ -0,0 +1,400 @@
+_	 31586
+e	 15008
+n	 9058
+i	 7299
+r	 6830
+t	 5662
+s	 5348
+a	 4618
+h	 4176
+d	 4011
+er	 3415
+en	 3412
+u	 3341
+l	 3266
+n_	 2848
+c	 2636
+ch	 2460
+g	 2407
+o	 2376
+e_	 2208
+r_	 2128
+m	 2077
+_d	 1948
+de	 1831
+en_	 1786
+ei	 1718
+er_	 1570
+in	 1568
+te	 1505
+ie	 1505
+b	 1458
+t_	 1425
+f	 1306
+k	 1176
+ge	 1144
+s_	 1137
+un	 1113
+,	 1104
+,_	 1099
+w	 1099
+z	 1060
+nd	 1039
+he	 1004
+st	 989
+_s	 952
+_de	 949
+.	 909
+_e	 906
+ne	 906
+der	 880
+._	 847
+be	 841
+es	 829
+ic	 796
+_a	 791
+ie_	 779
+is	 769
+ich	 763
+an	 755
+re	 749
+di	 732
+ein	 730
+se	 730
+"	 720
+ng	 709
+_i	 706
+sc	 683
+sch	 681
+it	 673
+der_	 652
+h_	 651
+ch_	 642
+S	 630
+le	 609
+p	 609
+ä	 607
+ü	 603
+au	 603
+v	 602
+che	 599
+_w	 596
+d_	 585
+die	 576
+_di	 572
+m_	 562
+_die	 559
+el	 548
+_S	 540
+_der	 529
+li	 527
+_der_	 523
+si	 515
+al	 514
+ns	 507
+on	 501
+or	 495
+ti	 490
+ten	 487
+ht	 486
+die_	 485
+_die_	 483
+D	 479
+rt	 478
+nd_	 476
+_u	 470
+nt	 468
+A	 466
+in_	 464
+den	 461
+cht	 447
+und	 443
+me	 440
+_z	 429
+ung	 426
+ll	 423
+_un	 421
+_ei	 419
+_n	 415
+hr	 412
+ine	 412
+_A	 408
+_ein	 405
+ar	 404
+ra	 403
+_v	 400
+_g	 400
+as	 395
+zu	 392
+et	 389
+em	 385
+_D	 380
+eine	 376
+gen	 376
+g_	 376
+da	 368
+we	 366
+K	 365
+lt	 360
+B	 354
+_"	 353
+nde	 349
+ni	 347
+und_	 345
+E	 345
+ur	 345
+_m	 342
+ri	 341
+ha	 340
+eh	 339
+ten_	 338
+es_	 336
+_K	 336
+_und	 335
+ig	 335
+_b	 335
+hen	 334
+_und_	 332
+_au	 329
+_B	 327
+_da	 325
+_zu	 324
+_in	 322
+at	 321
+us	 318
+wi	 307
+n,	 305
+n,_	 304
+nn	 304
+te_	 301
+eit	 301
+_h	 300
+ter	 299
+M	 298
+n.	 295
+ß	 294
+ng_	 289
+sche	 289
+-	 283
+rs	 282
+den_	 282
+_si	 280
+G	 280
+im	 278
+_ge	 277
+chen	 276
+rd	 273
+_E	 273
+n._	 270
+icht	 270
+rn	 268
+uf	 267
+isch	 264
+isc	 264
+nen	 263
+_in_	 262
+_M	 260
+_er	 257
+ich_	 255
+ac	 253
+lic	 252
+_G	 252
+ber	 252
+la	 251
+vo	 251
+eb	 250
+ke	 249
+F	 248
+as_	 248
+hen_	 248
+ach	 245
+en,	 244
+ung_	 243
+lich	 243
+ste	 243
+en,_	 243
+_k	 241
+ben	 241
+_f	 241
+en.	 241
+_be	 239
+it_	 239
+L	 238
+_se	 237
+mi	 236
+ve	 236
+na	 236
+on_	 236
+P	 235
+ss	 234
+ist	 234
+ö	 234
+ht_	 233
+ru	 233
+st_	 229
+_F	 229
+ts	 227
+ab	 226
+W	 226
+ol	 225
+_eine	 225
+hi	 225
+so	 224
+em_	 223
+"_	 223
+ren	 222
+en._	 221
+chen_	 221
+R	 221
+ta	 221
+ere	 220
+ische	 219
+ers	 218
+ert	 217
+_P	 217
+tr	 217
+ed	 215
+ze	 215
+eg	 215
+ens	 215
+ür	 213
+ah	 212
+_vo	 212
+ne_	 211
+cht_	 210
+uc	 209
+_wi	 209
+nge	 208
+lle	 208
+fe	 207
+_L	 207
+ver	 206
+hl	 205
+V	 204
+ma	 203
+wa	 203
+auf	 201
+H	 198
+_W	 195
+T	 195
+nte	 193
+uch	 193
+l_	 192
+sei	 192
+nen_	 190
+u_	 189
+_den	 189
+_al	 189
+_V	 188
+t.	 188
+lte	 187
+ut	 186
+ent	 184
+sich	 183
+sic	 183
+il	 183
+ier	 182
+am	 181
+gen_	 180
+sen	 179
+fü	 178
+um	 178
+t._	 177
+f_	 174
+he_	 174
+ner	 174
+nst	 174
+ls	 174
+_sei	 173
+ro	 173
+ir	 173
+ebe	 173
+mm	 173
+ag	 172
+ern	 169
+t,_	 169
+t,	 169
+eu	 169
+ft	 168
+icht_	 167
+hre	 167
+Be	 166
+nz	 165
+nder	 165
+_T	 164
+_den_	 164
+iche	 163
+tt	 163
+zu_	 162
+and	 162
+J	 161
+rde	 160
+rei	 160
+_we	 159
+_H	 159
+ige	 159
+_Be	 158
+rte	 157
+hei	 156
+das	 155
+aus	 155
+che_	 154
+_das	 154
+_zu_	 154
+tz	 154
+_ni	 153
+das_	 153
+_R	 153
+N	 153
+des	 153
+_ve	 153
+_J	 152
+I	 152
+_das_	 152
+men	 151
+_so	 151
+_ver	 151
+_auf	 150
+ine_	 150
+_ha	 150
+rg	 149
+ind	 148
+eben	 148
+kt	 147
+mit	 147
+_an	 147
+her	 146
+Ge	 146
+Sc	 145
+_sich	 145
+U	 145
+Sch	 145
+_sic	 145
+end	 145
+Di	 144
+abe	 143
+ck	 143
+sse	 142
+ür_	 142
+ell	 142
+ik	 141
+o_	 141
+nic	 141
+nich	 141
+sa	 141
+_fü	 140
+hn	 140
+zi	 140
+no	 140
+nicht	 140
+im_	 139
+von_	 139
+von	 139
+_nic	 139
+_nich	 139
+eine_	 139
+oc	 138
+wei	 138
+io	 138
+schen	 138
+gt	 138
diff --git a/libtextcat/data/new_fingerprints/lm/greek.lm b/libtextcat/data/new_fingerprints/lm/greek.lm
new file mode 100644
index 000000000000..6dff6cd4f767
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/greek.lm
@@ -0,0 +1,400 @@
+_	 89284
+α	 19666
+τ	 16086
+ο	 15826
+ε	 14848
+ι	 12766
+ν	 12189
+π	 8776
+σ	 8653
+ρ	 8399
+κ	 7761
+μ	 7529
+υ	 6850
+ά	 6284
+_τ	 5918
+λ	 5802
+ς	 5371
+α_	 5272
+η	 5236
+έ	 4739
+ί	 4609
+ό	 4489
+το	 4461
+ς_	 4111
+ου	 4075
+ι_	 4033
+ε_	 4019
+.	 3916
+_κ	 3897
+ο_	 3836
+._	 3810
+ν_	 3661
+_π	 3414
+_σ	 3333
+"	 3247
+_μ	 3242
+_το	 3118
+,	 3106
+,_	 3068
+γ	 3058
+_α	 2912
+ω	 2689
+να	 2593
+δ	 2455
+τα	 2420
+χ	 2411
+κα	 2406
+στ	 2406
+_ε	 2353
+-	 2335
+-_	 2192
+ύ	 2171
+αν	 2162
+τη	 2151
+ή	 2141
+υ_	 2133
+αι	 2100
+θ	 2053
+φ	 1989
+ου_	 1974
+ει	 1889
+_κα	 1882
+εί	 1864
+το_	 1802
+πο	 1771
+αι_	 1727
+σε	 1709
+_ν	 1647
+_"	 1619
+η_	 1609
+ια	 1602
+να_	 1518
+τι	 1501
+ον	 1501
+του	 1495
+με	 1460
+_του	 1407
+_έ	 1405
+_στ	 1396
+ώ	 1364
+πε	 1359
+τε	 1300
+μα	 1298
+β	 1274
+ρι	 1252
+ό_	 1241
+_δ	 1231
+ξ	 1223
+ντ	 1220
+_το_	 1196
+απ	 1187
+ρο	 1184
+_γ	 1183
+_τη	 1177
+ζ	 1158
+_εί	 1150
+ά_	 1150
+_να	 1124
+έν	 1115
+και	 1110
+_και	 1093
+αν_	 1082
+ρα	 1078
+και_	 1061
+_να_	 1060
+_και_	 1053
+μπ	 1049
+νο	 1048
+ατ	 1036
+ιο	 1024
+ια_	 1018
+ερ	 1003
+ού	 993
+_απ	 984
+σε_	 974
+ικ	 973
+_ο	 967
+εν	 947
+ος	 936
+ει_	 935
+πό	 901
+λο	 892
+_με	 890
+νε	 884
+του_	 871
+ον_	 869
+ας	 865
+_του_	 854
+ασ	 841
+με_	 840
+σα	 834
+κο	 833
+αρ	 832
+πρ	 824
+ίν	 820
+κά	 808
+_πο	 804
+πι	 796
+Κ	 796
+μέ	 783
+μο	 777
+έρ	 772
+αλ	 766
+ην	 762
+Μ	 759
+ισ	 745
+κε	 742
+τα_	 740
+στο	 738
+ω_	 730
+ην_	 728
+Ο	 717
+Τ	 714
+_φ	 711
+ετ	 705
+δε	 704
+πα	 697
+ας_	 688
+τά	 684
+ος_	 683
+_ό	 680
+_Κ	 675
+οι	 671
+_χ	 670
+την	 663
+την_	 658
+_στο	 647
+ή_	 645
+πό_	 638
+_θ	 633
+_ο_	 631
+",	 630
+_πρ	 626
+_Μ	 624
+ίπ	 624
+άν	 623
+",_	 623
+από	 620
+που	 619
+ότ	 618
+λα	 617
+τον	 617
+_από	 616
+μι	 612
+Ο_	 611
+ρε	 607
+υτ	 604
+λε	 595
+_λ	 594
+ρό	 590
+_με_	 586
+ιά	 580
+τον_	 577
+γι	 577
+_Ο	 575
+από_	 572
+άρ	 570
+πά	 570
+_από_	 569
+ρά	 562
+ταν	 554
+ένα	 553
+υν	 552
+που_	 551
+δι	 547
+τρ	 547
+τό	 544
+_β	 540
+χε	 536
+εν_	 534
+ησ	 528
+_Ο_	 525
+ης	 520
+".	 519
+_που	 516
+_Τ	 515
+"._	 513
+τη_	 512
+ς.	 510
+είπ	 508
+ταν_	 504
+_είπ	 503
+ς._	 501
+_τα	 500
+ξε	 497
+στο_	 496
+λλ	 493
+ακ	 492
+Α	 491
+_που_	 490
+άλ	 489
+ίπε	 489
+είπε	 485
+_είπε	 483
+_την	 483
+τι_	 482
+_την_	 481
+άτ	 480
+λι	 480
+_δε	 479
+άμ	 477
+_στο_	 475
+σο	 473
+_ά	 468
+"_	 463
+μέν	 463
+ιν	 461
+ις	 452
+_αν	 452
+κό	 451
+αυ	 451
+_τον	 450
+_γι	 449
+θα	 447
+ες	 446
+ση	 446
+_μι	 445
+_τον_	 443
+ε.	 441
+ε._	 441
+ους	 439
+λά	 439
+υς	 439
+ολ	 438
+πιο	 437
+ορ	 432
+_πα	 428
+_κά	 427
+τε_	 427
+αμ	 423
+;	 423
+_μο	 422
+σκ	 421
+της	 421
+_ξ	 418
+στη	 415
+Κά	 411
+νη	 408
+για	 405
+α.	 403
+κρ	 402
+κι	 402
+ς,	 402
+ς,_	 401
+α._	 398
+ηκ	 397
+_Κά	 397
+ελ	 396
+_έν	 395
+_ή	 393
+_μα	 392
+ία	 391
+ως	 391
+λη	 390
+ίνα	 389
+πί	 389
+μου	 388
+μά	 388
+_αυ	 387
+ης_	 386
+συ	 384
+ναι	 384
+Π	 383
+αυτ	 382
+ί_	 376
+μπι	 375
+ίσ	 372
+_της	 370
+_τα_	 367
+_για	 365
+_ένα	 362
+_μπ	 361
+θε	 361
+ιον	 359
+ις_	 358
+τή	 358
+_θα	 354
+_αυτ	 354
+άμπ	 352
+κ.	 352
+κ._	 351
+είν	 351
+ομ	 350
+ίναι	 348
+ντα	 348
+ναι_	 348
+ως_	 347
+χα	 346
+Ε	 346
+υ.	 346
+για_	 346
+υ._	 345
+δεν	 345
+ένα_	 345
+α,	 344
+α,_	 344
+δεν_	 344
+ύρ	 343
+όν	 343
+α-	 342
+ύσ	 341
+_κ.	 340
+στε	 339
+Κάμ	 339
+_κ._	 339
+τέ	 339
+α-_	 338
+ευ	 338
+ιλ	 338
+ρί	 338
+Κάμπ	 338
+_μου	 338
+_Κάμ	 338
+_Κάμπ	 337
+υμ	 336
+σει	 336
+πιον	 336
+μπιον	 336
+μπιο	 336
+_κο	 334
+Κάμπι	 334
+_η	 334
+άμπι	 334
+θα_	 333
+νι	 332
+της_	 331
+ψ	 331
+όμ	 330
+ησε	 330
+_σα	 329
+μα_	 328
+ός	 328
+Σ	 326
+_δεν	 325
+_δεν_	 325
+σμ	 324
+ες_	 324
+περ	 324
+ίχ	 323
+ίναι_	 323
+τικ	 322
+_ρ	 321
+άμπιο	 321
+υς_	 321
+ους_	 321
+_πε	 321
+σω	 320
+_για_	 320
+προ	 320
+γε	 318
+;"	 316
+;"_	 316
+Δ	 315
+τυ	 314
+ρα_	 313
+_συ	 312
+ρω	 312
+_θα_	 310
+όσ	 309
+ου.	 309
diff --git a/libtextcat/data/new_fingerprints/lm/hebrew.lm b/libtextcat/data/new_fingerprints/lm/hebrew.lm
new file mode 100644
index 000000000000..31b4ee0af280
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/hebrew.lm
@@ -0,0 +1,400 @@
+_	 81560
+י	 23072
+ו	 19215
+ה	 15606
+ל	 12612
+ר	 11293
+ת	 11070
+מ	 10090
+ב	 9648
+א	 9601
+ש	 9081
+ה_	 7811
+נ	 6685
+ע	 6326
+_ת	 5878
+ם	 5542
+ד	 5019
+ח	 4669
+_ם	 4570
+ב_	 4267
+כ	 3984
+_ה	 3812
+ק	 3769
+פ	 3699
+ל_	 3693
+םי	 3535
+מ_	 3489
+ס	 3374
+א_	 3362
+תו	 3130
+,	 3067
+_ל	 3037
+_,	 3035
+_י	 2936
+ש_	 2886
+_םי	 2840
+ג	 2768
+ט	 2626
+ן	 2424
+_ר	 2395
+_תו	 2291
+.	 2256
+צ	 2215
+_.	 2205
+ינ	 2144
+ע_	 2003
+_ן	 1959
+_ו	 1913
+"	 1815
+יב	 1797
+לש	 1742
+יל	 1687
+יר	 1665
+י_	 1647
+וי	 1620
+ו_	 1578
+ור	 1525
+תא	 1475
+כ_	 1469
+רו	 1411
+ז	 1383
+ונ	 1353
+מה	 1351
+תי	 1343
+יי	 1343
+לו	 1315
+יד	 1285
+רי	 1236
+מה_	 1211
+הל	 1206
+ומ	 1192
+ני	 1163
+רש	 1155
+יא	 1146
+אר	 1138
+_תא	 1137
+שי	 1134
+יש	 1087
+נ_	 1080
+לא	 1074
+וח	 1067
+_א	 1062
+שמ	 1059
+ימ	 1052
+הי	 1047
+-	 1024
+לש_	 1008
+וה	 973
+רב	 967
+וא	 954
+תא_	 951
+ול	 948
+_ד	 941
+יה	 896
+נו	 888
+וע	 883
+יכ	 873
+וש	 871
+לע	 867
+אל	 850
+עו	 843
+_-	 830
+ח_	 830
+דו	 824
+ןו	 820
+ר_	 806
+וב	 805
+_לש	 799
+יט	 784
+אה	 773
+_לש_	 748
+יע	 746
+די	 743
+_ש	 726
+_תא_	 723
+ך	 720
+_תי	 719
+-_	 716
+_-_	 713
+בי	 709
+בו	 706
+ות	 699
+אה_	 690
+רמ	 686
+שה	 683
+וד	 678
+יח	 675
+פ_	 672
+הנ	 669
+_ב	 668
+_ע	 659
+_ך	 655
+יס	 652
+ןי	 649
+_לע	 640
+יו	 635
+אמ	 635
+יב_	 632
+ת_	 631
+מא	 628
+שו	 627
+_ןו	 624
+לי	 624
+לע_	 621
+תה	 619
+ית	 600
+הל_	 599
+וכ	 599
+יפ	 596
+פה	 595
+וק	 586
+הש	 578
+עי	 575
+_ןי	 569
+מו	 564
+_לע_	 561
+קי	 560
+יג	 557
+יה_	 557
+רשי	 554
+םו	 548
+אל_	 548
+תוי	 548
+לאר	 546
+רא	 542
+הר	 540
+"_	 540
+מב	 539
+שה_	 538
+ופ	 538
+ארש	 535
+רע	 534
+חה	 533
+וג	 532
+ארשי	 530
+לארשי	 530
+לארש	 530
+או	 527
+מי	 525
+_יכ	 518
+המ	 518
+פה_	 511
+יכ_	 510
+_ינ	 509
+לכ	 506
+תמ	 502
+מב_	 500
+סו	 498
+חא	 497
+יק	 497
+וו	 494
+_ק	 485
+ג_	 481
+םיל	 477
+_הי	 477
+דמ	 472
+בה	 470
+,ה	 470
+_,ה	 470
+ק_	 469
+עב	 468
+_םו	 467
+הב	 467
+חה_	 466
+_יכ_	 463
+אב	 462
+רח	 462
+_אל	 461
+ץ	 455
+מל	 454
+יני	 454
+שא	 453
+רה	 453
+יצ	 452
+םיר	 451
+_הנ	 447
+טי	 443
+ד_	 441
+מע	 440
+םיי	 439
+וה_	 439
+'	 435
+אמ_	 430
+.ם	 429
+תנ	 429
+_.ם	 428
+רק	 427
+תר	 423
+וס	 417
+נש	 417
+_הל	 414
+סל	 413
+נת	 408
+ס_	 405
+סה	 400
+לפ	 400
+בש	 399
+,ם	 399
+_,ם	 399
+ממ	 397
+שי_	 396
+נב	 396
+עה	 394
+תה_	 393
+תונ	 393
+םינ	 389
+_רו	 385
+רמא	 384
+יא_	 384
+לב	 384
+תב	 381
+בר	 378
+בה_	 377
+טס	 374
+_ץ	 374
+עמ	 374
+חי	 373
+רפ	 373
+הו	 371
+חו	 370
+בל	 370
+_לא	 370
+קו	 367
+_הר	 366
+_םיר	 364
+חמ	 363
+ז_	 362
+_ח	 360
+נכ	 360
+_לו	 360
+כו	 359
+,ת	 358
+_,ת	 357
+מת	 356
+ינו	 353
+ורי	 353
+וא_	 349
+רד	 348
+תור	 348
+אי	 345
+ף	 345
+לשמ	 344
+כי	 340
+_םיל	 340
+וצ	 338
+תל	 338
+_םיי	 336
+רחא	 335
+_תוי	 335
+מא_	 332
+לח	 331
+_תר	 329
+_תונ	 325
+גי	 325
+עה_	 325
+:	 324
+פל	 324
+אב_	 324
+שר	 322
+רט	 321
+תש	 320
+צ_	 320
+מע_	 319
+וי_	 319
+_:	 319
+צמ	 316
+שממ	 315
+_ס	 315
+תינ	 315
+סמ	 315
+הד	 313
+רה_	 312
+וט	 312
+_ף	 310
+שאר	 309
+רשי_	 305
+ארשי_	 305
+.םי	 305
+_.םי	 304
+הת	 303
+יטס	 303
+_'	 303
+גה	 302
+שמ_	 302
+_םינ	 301
+לה	 298
+רג	 294
+חט	 293
+דע	 293
+םיד	 292
+אש	 292
+לשממ	 292
+םע	 292
+ידי	 290
+של	 289
+פו	 289
+דב	 289
+צו	 287
+_םע	 286
+,םי	 285
+_,םי	 285
+נמ	 284
+סי	 282
+שב	 282
+_רש	 281
+דר	 281
+_תור	 281
+קה	 280
+תוש	 278
+הש_	 276
+מל_	 276
+_אל_	 275
+והי	 274
+_לאר	 274
+פי	 274
+עב_	 271
+לא_	 271
+בא	 270
+חא_	 269
+חל	 268
+עפ	 267
+בע	 267
+.ה	 266
+_רי	 266
+_לארש	 266
+וני	 266
+_.ה	 265
+יטסל	 265
+טסל	 265
+ילא	 265
+תע	 264
+נה	 263
+קל	 262
+ניט	 260
+_.ת	 260
+.ת	 260
+פל_	 260
+הו_	 259
+סלפ	 258
+טסלפ	 258
+יטסלפ	 258
+ניטסל	 257
+ניטס	 257
+ומ_	 256
+סה_	 256
+מש	 255
+ירו	 255
+נש_	 254
+ומת	 254
+הה	 252
+בק	 251
+יש_	 251
+_ונ	 251
+ירב	 251
+_רב	 249
+_יד	 249
+_םיד	 249
+כה	 248
+גנ	 247
+_דו	 247
diff --git a/libtextcat/data/new_fingerprints/lm/hindi.lm b/libtextcat/data/new_fingerprints/lm/hindi.lm
new file mode 100644
index 000000000000..3b4e1584a943
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/hindi.lm
@@ -0,0 +1,400 @@
+_	 75620
+æ	 19109
+U	 16333
+ð	 11131
+¤	 11107
+·	 10241
+·¤	 7855
+Ú	 6993
+ÚU	 6598
+ç	 6322
+è	 6151
+Ù	 5887
+_·	 5800
+ã	 5370
+â	 5168
+U_	 5118
+æ_	 4935
+Ì	 4508
+×	 4467
+Ø	 4292
+ð_	 3962
+_·¤	 3937
+è_	 3904
+Â	 3718
+¤_	 3609
+Ü	 3563
+ãU	 3514
+_ç	 3394
+´	 3363
+ß	 2962
+¥	 2907
+ÚU_	 2851
+_¥	 2668
+_ã	 2632
+_â	 2575
+ô	 2527
+Î	 2513
+´_	 2512
+Á	 2451
+Uæ	 2336
+Õ	 2314
+_Â	 2280
+_×	 2260
+ñ	 2187
+¢	 2082
+»	 2078
+¤æ	 1988
+ð´	 1913
+·¤æ	 1886
+·ð	 1881
+ð¤	 1877
+·ð¤	 1860
+Ð	 1842
+Ð_	 1830
+·¤_	 1746
+é	 1714
+æð	 1703
+ð¤_	 1695
+·ð¤_	 1694
+æÚ	 1631
+ü	 1610
+_·ð	 1579
+_·ð¤	 1567
+ð´_	 1556
+æÚU	 1536
+Øæ	 1528
+Ùð	 1525
+Uè	 1515
+_·ð¤_	 1488
+Ù_	 1411
+Ùð_	 1407
+à	 1390
+_ãñ	 1357
+ãñ	 1357
+Å	 1337
+Ì_	 1319
+_Õ	 1315
+×ð	 1300
+ç·	 1279
+Ö	 1270
+_Á	 1258
+_·¤æ	 1209
+ç·¤	 1203
+¤è	 1195
+_Ù	 1187
+°	 1181
+§	 1166
+×ð´	 1163
+àæ	 1162
+ý	 1157
+¿	 1155
+_×ð	 1150
+×ð´_	 1140
+·¤è	 1127
+¤è_	 1092
+_×ð´	 1086
+_×ð´_	 1077
+ñU	 1075
+_ãU	 1071
+·¤è_	 1065
+ãñU	 1062
+_ãñU	 1062
+æÙ	 1053
+¥æ	 1052
+Ìæ	 1038
+¤Ú	 1035
+_ç·	 1009
+¤ÚU	 972
+âð	 970
+_ç·¤	 967
+_·¤è	 959
+ÚUæ	 936
+ãUæ	 930
+_·¤è_	 929
+·¤Ú	 928
+Í	 926
+_¥æ	 904
+ÅU	 904
+Ç	 904
+©	 890
+ê	 887
+©U	 885
+·¤ÚU	 866
+_©	 865
+_©U	 862
+_Ö	 854
+âð_	 850
+_Ú	 847
+_Ì	 837
+S	 834
+UÐ	 831
+_Î	 830
+UÐ_	 823
+_ß	 798
+Ùæ	 788
+â_	 783
+_ÚU	 773
+Uè_	 770
+ô´	 753
+æØ	 752
+Ï	 749
+Øæ_	 732
+×æ	 732
+ô_	 704
+_§	 704
+Áæ	 704
+_âð	 697
+Âý	 695
+ãUè	 693
+¤æ_	 690
+ü_	 688
+æÚU_	 685
+,	 684
+_»	 682
+·¤æ_	 679
+,_	 674
+_·¤Ú	 670
+¹	 665
+ðU	 664
+ßæ	 648
+_Âý	 647
+UÌ	 644
+Ü_	 643
+_Ü	 641
+ç·¤_	 639
+Ø_	 639
+Üæ	 633
+_âð_	 633
+æç	 623
+Uô	 621
+ô´_	 615
+_·¤ÚU	 611
+Uæ_	 599
+ãU_	 595
+Üð	 594
+UÙ	 589
+ñUÐ	 580
+_ãñUÐ	 580
+ãñUÐ	 580
+_°	 576
+_Áæ	 573
+ñUÐ_	 572
+ãñUÐ_	 572
+æÜ	 569
+_Ø	 569
+_Ùð	 569
+ÂÚ	 561
+_ç·¤_	 557
+	 556
+¤ô	 552
+ææ	 550
+ÂÚU	 549
+çß	 544
+Õæ	 538
+_·¤æ_	 535
+×_	 532
+çÜ	 525
+âæ	 523
+·¤ô	 519
+æð_	 502
+æ¢	 501
+¸	 498
+_Ùð_	 495
+	 494
+_ÂÚ	 493
+Âæ	 493
+Ìæ_	 490
+_ÂÚU	 485
+çÙ	 484
+õ	 481
+È	 478
+æ	 469
+.	 459
+ÂÚU_	 458
+Öæ	 449
+Øð	 449
+_çß	 445
+§â	 444
+¤ÚU_	 443
+Öè	 442
+_§â	 440
+_ÂÚU_	 439
+æð´	 437
+Ùæ_	 435
+	 434
+_¿	 433
+ÚUè	 431
+â¢	 431
+_·¤ô	 430
+Îð	 427
+æÌ	 425
+Î_	 420
+Öè_	 419
+¸U	 415
+	 412
+æ	 412
+§ü	 410
+´U	 405
+ÇU	 399
+»æ	 399
+·¤ÚU_	 394
+Uã	 394
+æÙ_	 393
+çÌ	 393
+¤ô_	 392
+·¤ô_	 392
+çÎ	 389
+ÚUÌ	 385
+æÁ	 385
+Ç¸	 383
+æð´_	 382
+Ìè	 381
+Íæ	 379
+çÚ	 375
+°_	 374
+ãUô	 374
+ÚUã	 374
+æÐ	 373
+æÐ_	 372
+_·¤ô_	 371
+_Õæ	 369
+æè	 364
+çÚU	 364
+ðU_	 362
+¤æð	 358
+È¤	 357
+Uæð	 354
+è´	 353
+â·	 352
+ß_	 350
+U·	 349
+¤æÚ	 346
+Ìð	 346
+·¤æð	 346
+æü	 345
+õÚ	 344
+õÚU	 342
+·¤æÚ	 342
+_×æ	 341
+_Öè	 341
+_çÜ	 340
+ñU_	 337
+_ãñU_	 337
+ÿ	 337
+ãñU_	 337
+Ùè	 336
+ãUè_	 334
+¿æ	 334
+ñ´	 334
+_Öè_	 332
+æ×	 327
+¤æÚU	 327
+ÿæ	 326
+_Í	 325
+U·¤	 323
+·¤æÚU	 323
+Uè´	 322
+ãUè´	 321
+_âæ	 320
+Ç¸U	 319
+_¥õ	 319
+¥õ	 319
+õÚU_	 319
+_ÚUã	 318
+Úð	 317
+è´_	 316
+_â¢	 316
+æ·	 313
+Øô	 310
+_ãUæ	 309
+Øã	 309
+À	 308
+ØãU	 308
+_Øã	 308
+_ØãU	 307
+_·¤æð	 304
+_¥õÚ	 304
+¥õÚ	 304
+_¥õÚU	 304
+_Öæ	 304
+¥õÚU	 304
+¥õÚU_	 303
+_çÙ	 303
+ãUè´_	 300
+Uè´_	 300
+_S	 300
+Îæ	 300
+UÜ	 298
+ÚUè_	 296
+æÎ	 296
+æß	 294
+ÅU_	 294
+Øð_	 293
+Ùã	 292
+âè	 291
+_Ùã	 290
+æè_	 290
+ðà	 290
+Üð_	 289
+UãU	 288
+ÙãU	 288
+Uâ	 288
+_ÙãU	 286
+_à	 286
+_ÙãUè	 285
+_Âæ	 285
+ÙãUè	 285
+æ·¤	 284
+_àæ	 284
+ÙãUè´	 283
+UÌ_	 282
+ãñ´	 280
+_ãñ´	 280
+ñ´U	 280
+â×	 279
+_çÎ	 278
+_ãñ´U	 278
+ãñ´U	 278
+»_	 277
+_Îð	 275
+ðàæ	 274
+àæ_	 273
+æñ	 272
+·¤ã	 272
+¤ã	 272
+Ìð_	 272
+_ãUô	 272
+æ_	 272
+-	 271
+¤ãU	 271
+·¤ãU	 271
+¢_	 271
+_·¤ã	 270
+ãUæ_	 270
+_·¤ãU	 269
+ÚUãU	 268
+ãé	 267
+æâ	 265
+°·	 263
+¤Ø	 263
+¤æð_	 262
+·¤æð_	 262
+°·¤	 262
+ÚðU	 258
+_°·	 258
+Ùè_	 258
+_°·¤	 257
+ÀU	 256
+v	 253
+ÂÙ	 252
+_ÚUæ	 252
+Üè	 249
+ç×	 247
+çâ	 246
+_Å	 246
+ÚUÙ	 246
+×é	 245
+._	 245
+UÚ	 244
+éU	 243
diff --git a/libtextcat/data/new_fingerprints/lm/hungarian.lm b/libtextcat/data/new_fingerprints/lm/hungarian.lm
new file mode 100644
index 000000000000..307348b47789
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/hungarian.lm
@@ -0,0 +1,400 @@
+_	 19186
+e	 5753
+a	 4627
+t	 4522
+s	 3480
+l	 3437
+n	 3137
+k	 3036
+i	 2527
+r	 2437
+z	 2399
+o	 2303
+á	 2039
+é	 1995
+g	 1978
+m	 1695
+y	 1338
+_a	 1256
+b	 1186
+d	 1148
+a_	 1108
+v	 1057
+t_	 901
+sz	 889
+el	 832
+,	 819
+,_	 818
+h	 792
+k_	 769
+.	 767
+et	 743
+gy	 711
+s_	 705
+_m	 702
+_a_	 695
+en	 671
+ö	 662
+n_	 646
+_k	 645
+j	 623
+._	 613
+i_	 606
+eg	 601
+p	 586
+_e	 580
+u	 579
+le	 576
+ó	 542
+er	 495
+f	 485
+ek	 477
+te	 477
+és	 473
+_s	 471
+al	 464
+ta	 458
+í	 453
+_h	 444
+_t	 442
+an	 426
+ze	 425
+me	 406
+at	 405
+l_	 401
+es	 395
+õ	 387
+y_	 381
+z_	 375
+tt	 374
+ke	 372
+_v	 369
+ás	 368
+ak	 367
+_é	 365
+ny	 363
+tá	 359
+c	 358
+re	 350
+to	 347
+A	 343
+e_	 340
+ü	 332
+ne	 330
+os	 326
+ál	 320
+_f	 320
+az	 317
+zt	 317
+ár	 317
+_n	 315
+ko	 312
+_A	 303
+_sz	 302
+is	 301
+ve	 299
+gy_	 297
+ít	 293
+_b	 293
+ra	 291
+or	 289
+ol	 284
+_i	 281
+em	 279
+_l	 274
+la	 264
+ez	 262
+be	 260
+lt	 260
+ok	 260
+ye	 256
+_me	 252
+on	 251
+en_	 247
+ar	 245
+_az	 245
+in	 243
+án	 242
+se	 242
+ég	 238
+egy	 237
+ha	 237
+r_	 237
+té	 237
+ér	 235
+sze	 233
+én	 226
+ly	 224
+g_	 221
+"	 221
+ll	 219
+iz	 214
+de	 214
+ek_	 213
+mi	 212
+rt	 211
+ba	 209
+ho	 209
+A_	 209
+és_	 209
+az_	 205
+va	 204
+ag	 203
+ka	 202
+na	 202
+og	 201
+ik	 201
+nt	 200
+_A_	 199
+ô	 199
+-	 198
+tt_	 198
+_az_	 197
+ni	 195
+cs	 194
+ki	 190
+kö	 187
+át	 187
+_eg	 187
+nd	 186
+fe	 185
+_és	 185
+lá	 182
+bi	 181
+nk	 180
+_le	 179
+an_	 179
+_és_	 177
+tás	 175
+ké	 174
+meg	 173
+_egy	 172
+ma	 171
+as	 170
+sa	 170
+sí	 169
+ge	 167
+ot	 167
+za	 167
+E	 166
+m_	 165
+_meg	 165
+_el	 165
+bb	 164
+ro	 164
+zá	 163
+he	 162
+má	 161
+sé	 160
+_r	 160
+sít	 160
+tos	 159
+ti	 159
+st	 158
+_j	 158
+él	 157
+it	 156
+_ho	 156
+ül	 156
+_ha	 155
+vé	 154
+am	 152
+oz	 152
+ele	 151
+ya	 151
+zto	 150
+ú	 149
+biz	 147
+so	 147
+et_	 145
+izto	 144
+izt	 144
+ap	 141
+"_	 141
+ed	 141
+ss	 140
+bizt	 140
+ék	 140
+bizto	 140
+iztos	 139
+ét	 139
+ztos	 139
+osít	 138
+zet	 138
+osí	 138
+mé	 137
+_is	 137
+t,	 136
+tosít	 136
+tosí	 136
+t,_	 136
+ó_	 135
+agy	 135
+ztosí	 135
+li	 134
+om	 134
+_fe	 134
+ere	 133
+ág	 133
+t.	 132
+nek	 131
+vi	 129
+_d	 129
+zo	 128
+k,_	 128
+k,	 128
+_kö	 127
+_p	 127
+M	 126
+let	 126
+ak_	 125
+já	 125
+ett	 125
+û	 124
+si	 124
+ész	 123
+_E	 123
+ép	 123
+vá	 123
+rá	 123
+t._	 123
+is_	 123
+S	 123
+ítás	 122
+ítá	 122
+kor	 121
+ai	 121
+fel	 120
+da	 120
+_mi	 120
+pe	 119
+ogy	 118
+ban	 118
+ad	 117
+ga	 116
+_va	 116
+ott	 114
+_ne	 114
+_ki	 113
+ör	 113
+zé	 112
+ben	 112
+_te	 111
+zi	 111
+sá	 110
+ség	 109
+do	 109
+tó	 108
+em_	 108
+_"	 108
+_ta	 108
+_M	 107
+ogy_	 107
+_á	 107
+k.	 106
+ól	 105
+_ke	 105
+_g	 104
+:	 103
+gye	 102
+ák	 102
+hog	 102
+ri	 102
+mo	 101
+ok_	 101
+:_	 101
+hogy	 101
+il	 101
+el_	 100
+zer	 100
+ete	 99
+nn	 99
+nak	 98
+je	 98
+sítá	 98
+szá	 98
+yo	 98
+osítá	 98
+sítás	 98
+_ké	 98
+_hog	 98
+lé	 97
+_S	 97
+_hogy	 97
+ig	 97
+_-	 96
+hogy_	 96
+ban_	 96
+ese	 95
+_bi	 94
+fo	 94
+ja	 94
+ul	 94
+õ_	 94
+k._	 94
+_c	 93
+ká	 91
+es_	 91
+ná	 91
+ény	 91
+gé	 91
+ás_	 91
+egy_	 90
+áb	 90
+rd	 89
+I	 89
+ány	 89
+_biz	 89
+_fel	 88
+öv	 88
+ala	 88
+szer	 88
+po	 88
+_ma	 88
+leg	 88
+tö	 88
+ket	 87
+un	 87
+di	 87
+ai_	 87
+nek_	 87
+rm	 86
+tal	 86
+év	 85
+_is_	 85
+nem	 85
+ti_	 84
+öz	 84
+szt	 84
+ut	 83
+ter	 83
+dé	 83
+kk	 83
+or_	 83
+b_	 82
+né	 82
+os_	 82
+re_	 82
+rs	 82
+_bizt	 82
+min	 82
+ben_	 81
+ra_	 81
+ik_	 81
+go	 80
+len	 80
+lm	 80
+öt	 80
+ely	 80
+aj	 80
+öl	 80
+_sze	 80
+_be	 79
+ev	 79
+ré	 79
+ssz	 79
+nt_	 79
+gya	 79
+K	 79
+si_	 79
+sza	 78
diff --git a/libtextcat/data/new_fingerprints/lm/icelandic.lm b/libtextcat/data/new_fingerprints/lm/icelandic.lm
new file mode 100644
index 000000000000..b1fe0f2c27dd
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/icelandic.lm
@@ -0,0 +1,400 @@
+_	 26104
+a	 6496
+r	 6044
+n	 5160
+i	 5123
+s	 3987
+e	 3891
+u	 3582
+t	 3300
+�	 3126
+l	 3071
+g	 2726
+m	 2459
+k	 2256
+f	 2230
+r_	 1967
+v	 1641
+ar	 1472
+�_	 1420
+_s	 1332
+�	 1248
+o	 1221
+�	 1197
+a_	 1155
+in	 1150
+i_	 1114
+h	 1023
+j	 975
+d	 974
+st	 929
+a�	 925
+.	 922
+n_	 875
+._	 875
+_v	 874
+m_	 854
+nn	 842
+_f	 840
+ur	 824
+_a	 806
+�	 785
+_h	 782
+�	 779
+i�	 771
+er	 765
+um	 727
+g_	 716
+y	 711
+_e	 709
+�	 672
+b	 672
+ir	 671
+ri	 670
+an	 667
+�	 650
+_�	 648
+a�_	 645
+u_	 633
+na	 631
+�_	 625
+ar_	 622
+_�	 608
+�_	 606
+_�	 595
+ta	 567
+ei	 566
+la	 558
+_m	 549
+_�_	 549
+um_	 547
+t_	 535
+ti	 529
+_o	 524
+ur_	 523
+_a�	 519
+i�_	 512
+�i	 496
+ve	 494
+og	 494
+�	 482
+og_	 479
+_og	 478
+_og_	 478
+nd	 469
+p	 464
+ra	 455
+un	 454
+ir_	 452
+_a�_	 451
+ni	 439
+en	 439
+�u	 439
+_�_	 436
+ng	 434
+il	 404
+ga	 395
+_t	 395
+nu	 393
+ki	 392
+ja	 383
+inn	 379
+_b	 375
+sk	 352
+s_	 350
+vi	 349
+r�	 347
+�a	 345
+ef	 339
+ag	 336
+_u	 330
+se	 324
+lu	 324
+af	 321
+_ve	 320
+tu	 318
+em	 307
+eg	 304
+nn_	 303
+_l	 303
+va	 301
+_k	 296
+,	 295
+ns	 292
+re	 292
+tt	 291
+,_	 291
+l_	 286
+am	 286
+es	 285
+yr	 285
+al	 281
+da	 277
+S	 275
+gu	 273
+_se	 271
+ver	 268
+_g	 266
+ing	 266
+_n	 262
+is	 258
+_er	 257
+sa	 256
+�ur	 255
+le	 255
+_st	 255
+_S	 254
+sem	 254
+ll	 254
+me	 253
+ha	 251
+li	 249
+kk	 249
+rs	 247
+_vi	 247
+rn	 246
+sl	 244
+gi	 243
+ss	 242
+rf	 241
+fy	 240
+�i_	 240
+mi	 238
+ka	 237
+ma	 231
+ld	 230
+�	 229
+rir	 227
+sta	 227
+fyr	 227
+v�	 227
+di	 226
+ru	 224
+var	 224
+_fy	 222
+ku	 221
+em_	 221
+nar	 220
+_sem_	 220
+_sem	 220
+sem_	 220
+he	 219
+yri	 217
+_fyr	 216
+si	 216
+yrir	 215
+au	 212
+er_	 212
+ek	 211
+_ha	 210
+�e	 209
+fyri	 207
+fyrir	 207
+_�e	 205
+fi	 204
+fr	 203
+ge	 201
+or	 200
+ne	 200
+ann	 198
+j�	 198
+_va	 196
+_fyri	 196
+_ver	 194
+fl	 192
+_er_	 191
+_um	 189
+�k	 188
+til	 187
+_he	 186
+fa	 186
+il_	 182
+_ti	 178
+_til	 177
+gar	 176
+_var	 176
+na_	 176
+�	 175
+e�	 171
+fu	 170
+nni	 169
+_me	 168
+ki_	 167
+vi�	 166
+ey	 165
+fn	 165
+arf	 164
+til_	 163
+st_	 162
+_til_	 162
+�a	 161
+num	 161
+_�a	 161
+as	 160
+_vi�	 160
+rt	 159
+el	 158
+u�	 156
+inn_	 155
+_um_	 154
+ra_	 153
+b�	 153
+tar	 151
+ta_	 151
+er�	 151
+�r	 148
+and	 148
+_sa	 146
+ig	 146
+_en	 146
+nga	 145
+rir_	 145
+us	 144
+jar	 143
+et	 143
+�r	 142
+_sk	 140
+ndi	 140
+��	 139
+var_	 139
+_r	 138
+av	 138
+�k	 137
+nna	 137
+�ur_	 136
+�l	 136
+ko	 135
+nin	 135
+vi�_	 135
+�l	 135
+ins	 134
+ik	 133
+E	 133
+K	 133
+yrir_	 133
+ns_	 133
+on	 133
+ein	 132
+_vi�_	 132
+�g	 132
+j�	 132
+�	 132
+�l	 132
+�s	 132
+_mi	 131
+f_	 131
+s�	 131
+sj	 131
+stu	 131
+nda	 130
+_var_	 130
+gr	 129
+�s	 128
+t�	 127
+ri_	 126
+haf	 126
+_s�	 125
+v�k	 124
+rin	 124
+te	 124
+r.	 124
+r._	 123
+H	 123
+nes	 123
+�t	 123
+ru_	 123
+kr	 122
+F	 122
+�r	 121
+num_	 121
+k_	 121
+a.	 121
+_H	 121
+_fr	 120
+_ge	 120
+r�	 120
+_E	 120
+_�	 120
+ug	 120
+ngu	 119
+an_	 119
+inga	 118
+_K	 118
+_haf	 118
+enn	 117
+ars	 117
+ri�	 117
+en_	 117
+sin	 116
+kur	 116
+it	 116
+�a_	 116
+ti_	 115
+r�i	 114
+tj	 114
+ni_	 114
+at	 114
+tarf	 114
+br	 113
+slu	 113
+kki	 113
+rg	 113
+m�	 113
+kv	 113
+_en_	 113
+a._	 112
+gar_	 112
+du	 112
+ju	 110
+ei�	 110
+und	 110
+lag	 110
+tur	 110
+ega	 109
+h�	 109
+��	 109
+gn	 109
+hef	 109
+kj	 109
+_hef	 109
+_sta	 108
+B	 108
+V	 108
+sam	 107
+_ei	 106
+_B	 106
+ft	 106
+ga_	 106
+G	 106
+_G	 105
+l�	 105
+kki_	 105
+star	 104
+in_	 104
+R	 104
+me�	 104
+_�r	 103
+_me�	 103
+ekk	 103
+inu	 103
+t�	 103
+_V	 103
+m.	 103
+a�i	 103
+j�	 102
+�j	 102
+_b�	 102
+ess	 102
+h�s	 101
+ut	 101
+gs	 101
+av�	 101
+mu	 101
+_R	 101
+_�	 101
+rst	 100
+�jar	 100
+leg	 100
+�ja	 100
+ja_	 99
+av�k	 99
diff --git a/libtextcat/data/new_fingerprints/lm/indonesian.lm b/libtextcat/data/new_fingerprints/lm/indonesian.lm
new file mode 100644
index 000000000000..3fa5a09b4691
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/indonesian.lm
@@ -0,0 +1,400 @@
+_	 19406
+a	 10666
+n	 5455
+e	 4535
+i	 4387
+r	 2936
+t	 2902
+an	 2853
+u	 2841
+k	 2761
+s	 2311
+m	 2178
+d	 2134
+g	 2105
+l	 1780
+a_	 1506
+n_	 1476
+ng	 1449
+p	 1397
+b	 1275
+an_	 1270
+o	 1246
+h	 1130
+i_	 1108
+er	 1038
+ka	 1032
+_d	 1006
+y	 997
+,	 951
+en	 941
+ar	 914
+,_	 900
+_m	 880
+ya	 842
+ta	 838
+ang	 797
+di	 787
+da	 773
+.	 754
+la	 742
+._	 738
+me	 732
+ak	 728
+_s	 718
+at	 690
+ra	 688
+ga	 683
+_k	 671
+_me	 650
+in	 628
+ah	 601
+_t	 583
+_p	 570
+g_	 551
+_b	 551
+_di	 548
+ng_	 544
+ma	 536
+se	 526
+tu	 511
+na	 506
+al	 500
+ri	 490
+as	 483
+k_	 482
+j	 480
+si	 470
+ny	 467
+h_	 457
+sa	 452
+ang_	 439
+it	 424
+kan	 423
+ti	 418
+_se	 417
+pe	 412
+S	 409
+ba	 407
+ke	 407
+em	 405
+men	 405
+be	 403
+un	 401
+te	 401
+am	 396
+pa	 395
+nya	 390
+_men	 374
+el	 374
+t_	 371
+_a	 360
+_i	 356
+u_	 355
+kan_	 345
+_ke	 339
+is	 335
+ah_	 324
+_S	 324
+eng	 321
+nga	 320
+ia	 318
+_pe	 316
+ha	 313
+ap	 311
+r_	 308
+w	 305
+li	 301
+_da	 300
+s_	 299
+P	 296
+nd	 290
+_be	 287
+ik	 283
+ja	 281
+yan	 281
+ad	 275
+ek	 273
+uk	 272
+di_	 270
+bu	 269
+ya_	 268
+yang	 268
+ak_	 266
+ber	 265
+_y	 265
+_ya	 264
+_P	 263
+ru	 260
+K	 259
+yang_	 256
+_yang	 256
+_yan	 256
+nt	 255
+de	 253
+_te	 250
+wa	 249
+et	 247
+at_	 246
+ara	 245
+gan	 243
+A	 237
+ari	 235
+ala	 230
+itu	 229
+c	 225
+ol	 225
+ni	 225
+us	 225
+dan	 224
+_K	 224
+M	 224
+B	 223
+ata	 222
+ai	 221
+ur	 219
+nya_	 217
+ua	 215
+_ka	 214
+_ber	 210
+eb	 209
+ran	 206
+D	 206
+ela	 206
+_di_	 205
+_l	 204
+ngan	 204
+ter	 203
+re	 201
+-	 199
+aka	 198
+l_	 194
+_A	 191
+era	 191
+a,	 191
+e_	 190
+ir	 187
+I	 186
+tan	 185
+_B	 184
+ut	 184
+ku	 183
+a,_	 183
+il	 182
+J	 181
+um	 180
+_it	 180
+_itu	 180
+_ta	 179
+su	 179
+dan_	 177
+es	 177
+on	 177
+or	 177
+_dan	 176
+lu	 174
+_M	 172
+tu_	 172
+_dan_	 172
+enga	 171
+mb	 169
+R	 169
+si_	 168
+per	 168
+gan_	 168
+ngan_	 165
+"	 162
+_ter	 162
+a.	 161
+man	 161
+gk	 160
+a._	 160
+asi	 160
+ngk	 160
+ep	 160
+ag	 159
+ul	 158
+da_	 157
+m_	 155
+du	 155
+ada	 153
+ki	 153
+rt	 150
+mp	 150
+T	 150
+ama	 148
+ing	 148
+na_	 147
+_J	 147
+_D	 145
+ung	 145
+ana	 145
+n,	 144
+ju	 144
+ud	 144
+rin	 143
+gi	 143
+aw	 141
+lah	 138
+lan	 138
+_sa	 136
+ri_	 136
+meng	 136
+_meng	 135
+_ma	 134
+n,_	 134
+awa	 134
+st	 134
+eka	 133
+mi	 133
+mu	 132
+_T	 132
+po	 131
+ge	 131
+ar_	 130
+id	 129
+ko	 129
+le	 128
+_h	 128
+ena	 127
+_j	 126
+emb	 126
+ina	 125
+_r	 124
+itu_	 124
+ay	 123
+ngg	 123
+gg	 123
+rang	 123
+pi	 120
+nan	 120
+_ba	 119
+_la	 119
+apa	 119
+_I	 118
+p_	 118
+bi	 117
+ai_	 117
+ta_	 116
+san	 116
+Ke	 116
+ro	 115
+eri	 114
+kar	 113
+lah_	 113
+_itu_	 112
+aya	 111
+i,	 110
+an,	 110
+ra_	 110
+_per	 110
+im	 110
+ika	 109
+isi	 109
+mem	 109
+tah	 108
+_Ke	 108
+ian	 108
+_mem	 108
+akan	 108
+Se	 108
+to	 107
+ab	 107
+ngka	 106
+rs	 106
+gka	 106
+uk_	 105
+seb	 104
+_de	 104
+pu	 104
+i,_	 104
+ita	 104
+nda	 103
+_ti	 103
+ni_	 103
+ca	 103
+_Se	 103
+ers	 103
+pen	 103
+ini	 102
+an,_	 102
+angk	 101
+uh	 101
+han	 101
+nta	 100
+_in	 99
+f	 99
+nj	 99
+ok	 99
+aga	 99
+_R	 98
+as_	 98
+tr	 98
+mer	 97
+lam	 97
+and	 97
+end	 96
+anga	 96
+ne	 96
+Sa	 96
+ka_	 96
+arin	 95
+gu	 95
+_ha	 94
+Z	 94
+al_	 94
+ga_	 94
+_Z	 93
+_pen	 93
+dar	 93
+Ad	 93
+i._	 93
+ada_	 93
+atan	 93
+tak	 93
+i.	 93
+ia_	 92
+asa	 92
+ap_	 92
+ari_	 92
+kat	 92
+_seb	 92
+_Za	 91
+Za	 91
+den	 91
+n.	 90
+_u	 90
+_Ad	 90
+engan	 89
+ib	 89
+any	 89
+n._	 89
+o_	 89
+Zar	 88
+Zari	 88
+rina	 88
+_Zar	 88
+_Zari	 88
+Zarin	 88
+arina	 88
+ks	 88
+angka	 87
+oli	 87
+eg	 87
+kt	 86
+_Sa	 86
+hu	 85
+ih	 85
+us_	 85
+adi	 85
+om	 85
+eba	 85
+anya	 85
+_bu	 84
+denga	 83
+L	 83
+ed	 83
+dak	 83
+deng	 83
+ma_	 82
+asi_	 82
diff --git a/libtextcat/data/new_fingerprints/lm/irish_gaelic.lm b/libtextcat/data/new_fingerprints/lm/irish_gaelic.lm
new file mode 100644
index 000000000000..b6874862da01
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/irish_gaelic.lm
@@ -0,0 +1,400 @@
+_	 8010
+a	 2622
+i	 1573
+h	 1334
+n	 1247
+r	 968
+_a	 847
+e	 830
+s	 817
+t	 747
+l	 639
+c	 636
+g	 598
+o	 590
+d	 554
+n_	 501
+a_	 487
+m	 432
+an	 415
+u	 413
+b	 379
+h_	 352
+ai	 350
+ch	 350
+ea	 346
+r_	 346
+í	 334
+é	 321
+_s	 309
+á	 306
+in	 281
+ar	 277
+.	 269
+_d	 266
+s_	 254
+ir	 253
+_b	 250
+f	 250
+an_	 246
+,	 241
+,_	 226
+ag	 225
+_an	 221
+bh	 218
+_c	 216
+._	 212
+ac	 210
+ha	 208
+_a_	 201
+"	 199
+_m	 199
+th	 198
+_t	 190
+ach	 182
+_ag	 180
+_an_	 179
+í_	 176
+_l	 168
+na	 168
+nn	 160
+e_	 159
+ar_	 158
+_g	 157
+ú	 156
+_i	 152
+il	 150
+le	 150
+is	 143
+ó	 142
+_bh	 138
+ei	 138
+g_	 135
+_f	 135
+dh	 135
+l_	 126
+t_	 125
+ig	 123
+é_	 122
+_n	 120
+gu	 120
+á_	 120
+mh	 118
+id	 117
+ch_	 117
+ad	 116
+he	 114
+ir_	 114
+ra	 109
+o_	 109
+ach_	 107
+ia	 105
+_ar	 105
+us	 104
+ui	 104
+_"	 101
+us_	 100
+T	 99
+am	 99
+ta	 98
+gus	 98
+gus_	 98
+_le	 97
+gh	 97
+_ch	 97
+agus	 94
+agus_	 94
+agu	 94
+éa	 93
+_agus	 93
+_agu	 93
+ean	 93
+na_	 92
+d_	 92
+ái	 91
+p	 89
+it	 89
+A	 89
+_ar_	 88
+rt	 86
+al	 85
+oi	 84
+sa	 84
+"_	 82
+hai	 81
+_r	 79
+nn_	 79
+hu	 79
+as	 79
+éi	 78
+_T	 78
+ma	 77
+air	 77
+at	 77
+ann	 76
+B	 76
+sé	 76
+hí	 75
+igh	 74
+st	 74
+ga	 73
+go	 71
+ua	 71
+ne	 71
+la	 71
+-	 71
+de	 71
+te	 71
+re	 70
+inn	 70
+ith	 69
+eac	 69
+_sé	 69
+in_	 68
+_go	 68
+hi	 68
+each	 68
+dh_	 68
+si	 67
+ag_	 67
+_go_	 66
+hea	 66
+go_	 66
+tha	 64
+om	 64
+_sé_	 63
+sé_	 63
+hí_	 63
+on	 62
+se	 61
+úi	 60
+nt	 60
+C	 60
+D	 59
+i_	 58
+_ag_	 58
+is_	 58
+ío	 58
+_de	 57
+_B	 56
+il_	 56
+or	 56
+_th	 54
+ca	 53
+fa	 53
+amh	 53
+_A	 53
+le_	 52
+?	 52
+S	 51
+io	 51
+_in	 51
+sí	 51
+li	 51
+rai	 50
+hf	 50
+ht	 50
+eo	 50
+sc	 50
+ri	 49
+:	 49
+igh_	 49
+gh_	 49
+_sí	 49
+:_	 49
+há	 49
+_D	 49
+be	 49
+aig	 49
+hé	 48
+oc	 48
+idh	 48
+rt_	 48
+ho	 47
+os	 47
+ann_	 47
+_C	 46
+!	 46
+Bh	 46
+bhf	 45
+_si	 45
+lt	 45
+_bhf	 45
+irt	 45
+ear	 44
+_na	 44
+ta_	 44
+air_	 44
+_p	 44
+im	 44
+aga	 44
+_ma	 44
+_S	 44
+aigh	 43
+án	 43
+_dh	 43
+uai	 43
+ao	 43
+cht	 43
+ain	 42
+bhe	 42
+ait	 42
+fh	 42
+sa_	 41
+m_	 41
+adh	 41
+ile	 41
+_é	 41
+ail	 41
+eir	 41
+ói	 41
+_Bh	 40
+as_	 40
+cha	 40
+idh_	 40
+hái	 39
+_i_	 39
+bh_	 39
+th_	 39
+ad_	 39
+och	 39
+mh_	 39
+tr	 39
+rea	 38
+_se	 38
+ro	 38
+rí	 38
+hair	 38
+_is	 38
+uil	 37
+iú	 37
+áin	 37
+I	 37
+ll	 37
+mé	 37
+_be	 36
+ba	 36
+eann	 36
+tá	 36
+_o	 36
+M	 36
+aid	 36
+aith	 36
+ib	 36
+'	 36
+tea	 36
+_mé	 35
+chu	 35
+ibh	 35
+each_	 35
+ean_	 34
+irt_	 34
+_na_	 34
+N	 34
+ist	 34
+fu	 34
+mha	 34
+bea	 34
+h.	 34
+_bhe	 34
+lá	 34
+ic	 34
+_sí_	 33
+eis	 33
+bhí	 33
+ni	 33
+héa	 33
+_sa	 33
+ith_	 33
+sí_	 33
+har	 33
+_bhí	 33
+ig_	 32
+ur	 32
+aí	 32
+hr	 32
+_am	 32
+_bhí_	 31
+da	 31
+úir	 31
+hfu	 31
+_chu	 31
+ol	 31
+ne_	 31
+_fa	 31
+An	 31
+Bhí_	 31
+Bhí	 31
+n,	 31
+_ac	 31
+bhí_	 31
+_bhfu	 30
+_ó	 30
+ana	 30
+_M	 30
+mé_	 30
+_fh	 30
+aigh_	 30
+bhfu	 30
+_mé_	 30
+tú	 29
+_le_	 29
+tá_	 29
+hean	 29
+háin	 29
+sin	 29
+eir_	 29
+nne	 29
+cé	 29
+_aga	 29
+h._	 29
+Tá	 29
+ibh_	 29
+iste	 28
+An_	 28
+do	 28
+hui	 28
+fui	 28
+ní	 28
+ste	 28
+acht	 28
+n,_	 28
+co	 28
+dea	 28
+ng	 28
+nach	 28
+id_	 28
+hfui	 28
+..	 28
+lei	 28
+nac	 28
+ce	 27
+a.	 27
+c_	 27
+lea	 27
+hfuil	 27
+_Bhí_	 27
+_bea	 27
+adh_	 27
+di	 27
+fuil	 27
+."	 27
+Tá_	 27
+ha_	 27
+ú_	 27
+uil_	 27
+."_	 27
+bhfui	 27
+_Bhí	 27
+éan	 27
+_do	 27
+lta	 27
+aoi	 27
+_lei	 27
+_mh	 26
+dú	 26
+fuil_	 26
+eat	 26
+-_	 26
+teac	 26
+ath	 26
diff --git a/libtextcat/data/new_fingerprints/lm/italian.lm b/libtextcat/data/new_fingerprints/lm/italian.lm
new file mode 100644
index 000000000000..543cadcfa88e
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/italian.lm
@@ -0,0 +1,400 @@
+_	 25028
+a	 7570
+e	 6477
+i	 5481
+o	 5104
+l	 3905
+n	 3866
+r	 3502
+t	 2934
+c	 2862
+s	 2862
+a_	 2504
+e_	 2404
+d	 2004
+i_	 1749
+o_	 1679
+u	 1650
+v	 1611
+p	 1561
+m	 1414
+_c	 1325
+,	 1192
+,_	 1192
+_s	 1190
+_d	 1094
+g	 1067
+an	 925
+er	 915
+_a	 914
+_p	 895
+la	 858
+_l	 830
+re	 799
+ar	 769
+h	 762
+no	 753
+co	 726
+va	 698
+_e	 657
+n_	 656
+on	 656
+ra	 653
+to	 651
+f	 638
+di	 638
+_i	 634
+ch	 634
+ll	 633
+l_	 624
+la_	 598
+ta	 593
+el	 576
+in	 567
+_m	 558
+en	 529
+b	 528
+ri	 525
+_co	 523
+_n	 523
+_di	 522
+li	 513
+av	 507
+al	 501
+le	 494
+ia	 492
+se	 484
+ol	 479
+_f	 477
+or	 477
+te	 469
+_e_	 467
+ve	 454
+at	 449
+de	 447
+.	 443
+ne	 429
+va_	 428
+ca	 426
+._	 422
+tt	 422
+re_	 415
+nt	 415
+io	 411
+_v	 407
+pe	 405
+z	 392
+to_	 391
+_ch	 389
+na	 384
+si	 384
+'	 383
+he	 382
+no_	 379
+ci	 374
+_la	 373
+ro	 371
+_g	 370
+st	 368
+cc	 366
+he_	 362
+di_	 362
+ma	 358
+ev	 354
+che	 354
+es	 352
+me	 352
+pa	 351
+_t	 349
+ti	 348
+_di_	 347
+ss	 345
+che_	 344
+a,_	 337
+a,	 337
+nd	 335
+o,	 333
+o,_	 333
+ell	 330
+gl	 323
+sa	 322
+il	 322
+gli	 321
+da	 318
+as	 318
+do	 314
+_che	 308
+_che_	 306
+eva	 306
+_la_	 300
+lla	 298
+le_	 293
+un	 291
+_pe	 290
+_de	 288
+q	 283
+qu	 283
+ava	 280
+po	 277
+on_	 275
+r_	 273
+li_	 273
+_b	 269
+_il	 268
+_il_	 268
+il_	 268
+lo	 267
+om	 263
+e,	 263
+e,_	 263
+ni	 258
+tr	 258
+so	 255
+ra_	 253
+os	 251
+_in	 249
+_u	 248
+per	 244
+are	 243
+et	 243
+_se	 240
+ano	 239
+si_	 238
+_ca	 238
+_qu	 238
+lla_	 238
+_q	 238
+_a_	 236
+ac	 236
+_r	 234
+ic	 233
+_no	 232
+ie	 227
+fa	 227
+hi	 226
+del	 225
+ua	 222
+_per	 218
+ce	 218
+_ma	 216
+sc	 216
+_del	 215
+mi	 212
+_un	 208
+chi	 206
+era	 205
+i,	 205
+i,_	 205
+su	 203
+and	 202
+vo	 202
+_fa	 201
+eva_	 200
+ano_	 199
+gli_	 197
+non	 196
+pi	 196
+vi	 195
+er_	 195
+_al	 194
+se_	 193
+_ne	 192
+_non	 191
+am	 190
+is	 187
+ava_	 187
+_non_	 186
+non_	 186
+in_	 185
+ent	 185
+_si	 184
+_pa	 184
+com	 183
+!	 182
+_le	 182
+_su	 181
+uo	 181
+el_	 180
+!_	 180
+l'	 178
+ue	 177
+te_	 177
+_com	 177
+are_	 176
+pr	 176
+_in_	 176
+van	 172
+mo	 172
+ta_	 171
+gn	 167
+ere	 166
+na_	 166
+tto	 163
+it	 161
+_per_	 161
+per_	 161
+é	 161
+all	 160
+ess	 159
+ut	 159
+col	 158
+acc	 157
+gi	 155
+lo_	 154
+oc	 154
+vano	 153
+io_	 153
+_av	 151
+ndo	 151
+é_	 151
+ato	 149
+ave	 148
+_st	 147
+me_	 147
+'a	 146
+ia_	 144
+con	 143
+mp	 143
+fi	 142
+ett	 142
+_si_	 141
+_pi	 140
+era_	 140
+ti_	 140
+ó	 140
+vano_	 140
+_gl	 139
+qua	 139
+ella	 139
+sta	 138
+ome	 137
+S	 137
+_gli	 137
+_S	 137
+ad	 136
+_ve	 134
+ant	 134
+ne_	 134
+ó_	 133
+sp	 133
+do_	 133
+_po	 132
+ro_	 132
+ov	 132
+_le_	 131
+ella_	 130
+sse	 129
+_con	 128
+ir	 128
+_vi	 128
+ig	 127
+_gli_	 127
+_ave	 127
+vev	 127
+un_	 126
+ot	 126
+veva	 125
+dell	 125
+que	 125
+a.	 125
+_o	 125
+a._	 124
+tu	 124
+cia	 123
+za	 123
+_que	 123
+_da	 121
+par	 121
+_pr	 120
+cch	 120
+_dell	 120
+eg	 119
+_sa	 119
+o._	 119
+o.	 119
+_col	 118
+lt	 118
+_un_	 118
+rt	 118
+ur	 117
+_vo	 117
+_me	 117
+ome_	 117
+L	 116
+ap	 116
+_L	 116
+zi	 116
+nto	 116
+og	 115
+_an	 115
+_so	 115
+em	 114
+ag	 114
+be	 111
+ni_	 111
+im	 110
+cchi	 110
+ver	 110
+lle	 109
+nz	 109
+cci	 109
+_ri	 109
+nc	 108
+_er	 108
+come_	 107
+come	 107
+aveva	 107
+ui	 107
+avev	 107
+tto_	 107
+_come	 106
+ed	 106
+P	 105
+man	 105
+_P	 105
+rs	 105
+occ	 104
+ndo_	 103
+ato_	 103
+_qua	 103
+_era	 103
+ari	 102
+ba	 100
+_mo	 100
+nel	 100
+id	 99
+men	 98
+_fi	 98
+_all	 98
+rr	 97
+_do	 97
+_avev	 97
+att	 97
+l'a	 96
+ei	 96
+zz	 96
+;	 96
+vol	 95
+pp	 95
+tra	 95
+;_	 95
+ere_	 94
+lle_	 94
+nda	 94
+utt	 94
+est	 93
+_nel	 93
+ul	 92
+ola	 92
+iv	 92
+ando	 90
+ale	 90
+lu	 90
+rn	 90
+e.	 89
+e._	 89
+ll'	 89
+tta	 88
+nte	 87
+_l'	 87
+uel	 87
diff --git a/libtextcat/data/new_fingerprints/lm/japanese.lm b/libtextcat/data/new_fingerprints/lm/japanese.lm
new file mode 100644
index 000000000000..654341bfeae2
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/japanese.lm
@@ -0,0 +1,400 @@
+_
+の
+、
+に
+を
+と
+し
+た
+な
+て
+。
+で
+る
+か
+す
+は
+り
+い
+ま
+ら
+く
+が
+　
+。_
+っ
+も
+_　
+して
+す。
+１
+地
+から
+う
+き
+だ
+ます
+年
+ー
+中
+れ
+め
+ます。
+」
+た。
+大
+分
+「
+ス
+した
+け
+こ
+人
+国
+政
+ん
+学
+って
+方
+りま
+った
+する
+改革
+革
+改
+的
+は、
+ち
+さ
+２
+あ
+て、
+部
+ど
+生
+てい
+タ
+会
+ン
+９
+よ
+果
+せ
+わ
+ると
+地方
+に、
+行
+や
+す。_
+３
+力
+自
+とし
+レ
+立
+)
+として
+_)
+なり
+でき
+進
+月
+新
+ります
+水
+同
+女
+下
+ります。
+作
+(_
+こと
+実
+役
+権
+いた
+(
+してい
+ル
+ク
+（
+み
+ニ
+ね
+つ
+きる
+そ
+経
+６
+時
+強
+家
+性
+５
+内
+調
+集
+る。
+上
+財
+改革(
+安
+的な
+事
+務
+」と
+一
+った。
+子
+全
+できる
+川
+た。_
+次
+業
+ない
+ド
+）
+現
+革(_
+０
+る。_
+改革(_
+革(
+です
+で、
+マ
+ミ
+ジ
+社
+でも
+目
+年から
+発
+省
+、中
+ア
+べ
+ッ
+ば
+済
+女性
+％
+法
+なん
+え
+画
+地方分権
+なく
+民
+構
+根
+し、
+が、
+高
+推
+施
+とい
+何
+電
+調査
+際
+も、
+和
+分権
+効
+限
+地方分
+国の
+長
+経済
+設
+計
+方分権
+野
+重
+小
+にな
+構造
+本
+校
+査
+しま
+造
+ます。_
+なりま
+れた
+方分
+あり
+財政
+理
+な_
+した。
+年か
+約
+_て
+１年
+よう
+私
+・
+メ
+育
+セ
+ビ
+シ
+して、
+ナ
+カ
+ト
+生の
+着
+ほ
+流
+構造改
+んて
+バ
+ろ
+菌
+治
+時に
+％、
+気
+お
+ドレ
+なっ
+など
+たり
+何か
+るこ
+、そして
+てく
+たち
+では
+ては
+進め
+造改
+構造改革(
+の子
+率
+期
+度
+日
+部省
+計画
+く_
+族
+文
+構造改革
+という
+します
+なった
+局
+踊り
+なんて
+正
+夫
+増
+多
+食
+使
+だった
+戻
+くな
+いま
+体
+スを
+題
+たが、
+いる
+いう
+身
+もな
+い。
+中部
+かけ
+踊
+_す
+面
+_に
+だった。
+的に
+門
+ドレス
+レス
+２年
+ました
+制
+合
+します。
+まで
+まし
+ありま
+く、
+冬
+とを
+文部省
+を進め
+推進
+元
+そし
+頃
+農
+入
+域
+解
+ている
+ら、
+、そし
+と、
+造改革
+家族
+見
+規
+した。_
+要
+８
+５年
+あります。
+葉
+０％
+造改革(
+あります
+公
+はな
+にあ
+しな
+結果
+表
+めた
+そして
+だけ
+だっ
+_す。
+４
+第
+ことを
+います
+文部
+の目
+、そ
+を進
+効果
+ること
+のま
+ある
+３０
+、地
+自分
+組
+結
+　「
+にも
+たが
+造改革(_
+る限り
+く女性た
+ナ増強
+戻る。
+った。_
+現す
diff --git a/libtextcat/data/new_fingerprints/lm/korean.lm b/libtextcat/data/new_fingerprints/lm/korean.lm
new file mode 100644
index 000000000000..159493270c3f
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/korean.lm
@@ -0,0 +1,400 @@
+_	 11636
+À	 2659
+°	 1629
+Ç	 1578
+¸	 1458
+¿	 1397
+´	 1299
+µ	 1118
+Á	 1005
+±	 928
+»	 849
+¼	 840
+_À	 809
+¹	 808
+º	 780
+¡	 773
+Ã	 764
+³	 674
+¾	 640
+Ì	 591
+Î	 580
+ÀÌ	 538
+½	 526
+Ï	 519
+Â	 518
+_°	 518
+Ù	 506
+·	 483
+È	 464
+ö	 463
+	 454
+´Ù	 451
+ø	 404
+Æ	 395
+ë	 384
+_¿	 382
+í	 377
+.	 374
+Å	 373
+ç	 358
+._	 347
+_Ç	 344
+´Â	 338
+¡_	 333
+Â_	 329
+¿¡	 327
+_Á	 319
+´Â_	 317
+´Ù.	 313
+Ù.	 313
+â	 308
+¶	 308
+´Ù._	 301
+Ù._	 301
+»_	 299
+_¹	 291
+î	 288
+®	 282
+À»	 279
+Ö	 278
+¦	 274
+À»_	 271
+Î_	 269
+,	 266
+Ñ	 266
+°í	 261
+Áö	 258
+,_	 258
+°¡	 250
+ß	 248
+_¼	 246
+Ä	 245
+ÀÇ	 244
+Ì_	 243
+_¸	 243
+_µ	 242
+ü	 238
+é	 235
+¼	 234
+ÀÌ_	 234
+ÇÏ	 234
+_±	 233
+´ë	 228
+·Î	 227
+ÇÑ	 222
+½Ã	 222
+_³	 215
+±â	 212
+_Ã	 210
+í_	 208
+_´	 206
+¦_	 206
+Ç_	 205
+_¾	 205
+º_	 204
+÷	 198
+Àº	 198
+°í_	 194
+·Î_	 193
+ó	 193
+¿¡_	 193
+¸¦_	 192
+¸¦	 192
+_ÀÌ	 190
+_	 189
+Àº_	 189
+_½	 189
+µµ	 188
+ÀÏ	 188
+ÀÇ_	 188
+_º	 186
+Í	 177
+Ú	 175
+ú	 171
+»ç	 161
+Ô	 154
+_ÀÏ	 153
+Ø	 152
+¿ø	 151
+±¸	 150
+µ¿	 147
+Ò	 147
+¸¸	 145
+¼ö	 143
+¤	 142
+ºÎ	 142
+_»	 141
+ÀÖ	 140
+æ	 139
+Ð	 138
+ù	 138
+ª	 137
+µé	 136
+è	 134
+À¸	 134
+_ÀÖ	 133
+²	 132
+Ñ_	 127
+ÀÎ	 125
+°¡_	 123
+ÀÚ	 122
+ÇÑ_	 121
+Àü	 121
+¾Æ	 118
+ý	 117
+å	 116
+Ï_	 115
+¾î	 115
+µ_	 115
+¢	 114
+Ö´	 113
+°ú	 112
+¸·	 111
+¯	 109
+ÇØ	 109
+§	 108
+à	 108
+_È	 108
+±¹	 107
+¼_	 107
+×	 107
+£	 106
+ÀÖ´	 105
+È¸	 103
+¸®	 101
+ö_	 101
+û	 100
+_ÀÖ´	 100
+Ãµ	 100
+¸·Î	 100
+"	 98
+À¸·Î	 97
+ÁÖ	 97
+À¸·	 97
+Àå	 95
+_´ë	 94
+¡¼	 94
+³ª	 94
+_½Ã	 94
+¥	 94
+µî	 94
+Á¤	 92
+°ø	 92
+_Å	 91
+á	 91
+Ï°	 90
+ÇÐ	 90
+¸·Î_	 90
+Ê	 89
+©	 89
+Í_	 89
+¸_	 89
+À¸·Î_	 89
+éÀ	 89
+Þ	 88
+¡¼	 88
+¿¡¼	 88
+¿¡¼	 88
+ê	 87
+µµ_	 87
+±³	 85
+_Æ	 85
+î_	 84
+°æ	 84
+µéÀ	 84
+¸í	 84
+ëÇ	 83
+¿ù	 83
+_Áö	 82
+ÇÏ°	 82
+¿À	 81
+¶ó	 80
+¿¡¼_	 79
+¡¼_	 79
+ÀÏ_	 78
+Ý	 78
+Á¦	 78
+ç_	 78
+øÀ	 78
+'	 77
+Çß	 77
+ì	 77
+Ü	 77
+Áß	 77
+ú_	 76
+Áö_	 76
+Ó	 76
+â_	 75
+(	 74
+)	 74
+»ó	 74
+°ü	 74
+»ý	 73
+_¿ù	 72
+_°¡	 72
+_¼ö	 72
+-	 72
+¿©	 72
+Ö´Ù	 72
+º¸	 71
+ÀÖ´Ù	 71
+»ê	 70
+°³	 70
+½º	 70
+¼±	 69
+¿ë	 69
+°ú_	 69
+_ÀÖ´Ù	 69
+_µî	 69
+ø_	 69
+ß´	 69
+°Í	 68
+³»	 68
+_¡	 68
+_ÇÑ	 68
+ù_	 67
+Ã¼	 67
+¸¿	 66
+_ÀÏ_	 66
+Çß´	 66
+°Ô	 65
+ñ	 65
+_¶	 65
+_°Í	 65
+Çß´Ù	 64
+ß´Ù	 64
+_ÇÏ	 63
+¹Î	 62
+«	 62
+Ï´	 62
+¼Ò	 62
+¿ù_	 62
+Á¶	 61
+³â	 61
+Ï°í	 61
+Ì´	 60
+¾È	 60
+ÇÏ°í	 60
+õ	 59
+_¿ù_	 59
+_¼	 59
+Åë	 59
+ÆÄ	 58
+®_	 58
+_¸¸	 58
+Ø_	 58
+´ç	 57
+ß´Ù.	 57
+¬	 57
+Õ	 57
+Çß´Ù.	 57
+¹°	 57
+¾÷	 57
+Ö´Ù.	 56
+ß_	 56
+ÀÖ´Ù.	 56
+¿Í	 56
+ß´Ù._	 56
+Áø	 56
+Àç	 55
+¸°	 55
+ÍÀ	 55
+Æ®	 55
+¹é	 55
+ÀÌ´	 55
+Ö´Ù._	 54
+_¹é	 54
+¿Í_	 53
+Àû	 53
+ð	 53
+¹®	 53
+_ÁÖ	 53
+´Ü	 53
+¼º	 53
+ÇØ_	 53
+°Ç	 53
+íÀ	 52
+_Àü	 52
+Ô_	 52
+¿¬	 52
+_°æ	 51
+°ÍÀ	 51
+°£	 51
+¿ì	 51
+È	 51
+ä	 50
+_¾Æ	 50
+´ëÇ	 50
+Ä¡	 50
+Ï°í_	 49
+ÇÏ°í_	 49
+_ÀÎ	 49
+Û	 49
+É	 49
+_"	 48
+öµ	 48
+À§	 48
+ÀÌ´Ù	 48
+ÀÔ	 48
+_°ÍÀ	 48
+Ì´Ù	 48
+¡	 47
+Ì´Ù.	 47
+_°ø	 47
+ÀÌ´Ù.	 47
+°Ô_	 47
+_»ç	 47
+¸ç	 47
+½Å	 47
+Ã_	 46
+ÅÍ	 46
+é_	 46
+Ò_	 46
+ï	 46
+ÇÏ´	 46
+_°³	 45
+_´Ù	 45
+_ÀÚ	 45
+¸¶	 45
+°è	 45
+Çà	 45
+Ì´Ù._	 45
+÷À	 44
+îÁ	 44
+ÈÄ	 44
+±â_	 43
+(_	 43
+¸é	 43
+¿	 43
+ü_	 43
+ºñ	 42
+´	 42
+ë_	 42
+ÀÎ_	 42
+_ÀÌ_	 42
+µî_	 42
+°	 42
+ÎÃ	 41
+µÇ	 41
+¿øÀ	 41
+¿µ	 41
+À½	 40
+ÎÃµ	 40
+±×	 40
+Ë	 40
+¿¹	 40
+_¿À	 40
+øÇ	 40
+¸»	 40
+_ÇÐ	 40
+¡_	 39
+_³â	 39
+³²	 39
+ÇÒ	 39
+¿_	 39
+_³ª	 39
+³	 38
+¸íÀ	 38
+âÀ	 38
+ª_	 38
diff --git a/libtextcat/data/new_fingerprints/lm/latin.lm b/libtextcat/data/new_fingerprints/lm/latin.lm
new file mode 100644
index 000000000000..177cd35aa174
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/latin.lm
@@ -0,0 +1,400 @@
+_	 20136
+e	 6892
+i	 5604
+a	 5443
+u	 4581
+t	 4552
+s	 4354
+r	 3923
+n	 3375
+m	 3063
+o	 2921
+c	 2224
+l	 1805
+e_	 1625
+s_	 1503
+p	 1424
+d	 1397
+,	 1285
+,_	 1276
+er	 1077
+qu	 1028
+q	 1028
+a_	 1019
+t_	 1018
+is	 942
+_a	 921
+re	 902
+m_	 891
+v	 858
+b	 821
+um	 808
+_s	 773
+us	 772
+en	 766
+nt	 733
+in	 729
+ue	 727
+te	 720
+g	 718
+_i	 710
+_p	 679
+it	 676
+_c	 669
+et	 653
+que	 652
+_e	 643
+at	 643
+ue_	 616
+ra	 614
+que_	 611
+f	 601
+or	 598
+ri	 576
+ti	 572
+ta	 559
+tu	 552
+an	 551
+ae	 527
+_m	 513
+am	 501
+_t	 493
+us_	 488
+is_	 487
+es	 479
+em	 479
+_f	 451
+um_	 443
+_v	 442
+ia	 442
+li	 438
+_d	 436
+.	 432
+i_	 430
+et_	 429
+ni	 412
+ne	 409
+h	 406
+de	 404
+ur	 396
+._	 392
+ar	 388
+os	 388
+mi	 382
+pe	 382
+la	 376
+st	 371
+s,	 368
+di	 367
+_et	 366
+s,_	 365
+_in	 363
+on	 360
+o_	 359
+_n	 351
+_et_	 351
+as	 346
+im	 336
+na	 327
+se	 320
+ma	 315
+cu	 307
+vi	 306
+si	 303
+ro	 303
+r_	 302
+su	 299
+un	 295
+_l	 291
+to	 291
+ec	 290
+ci	 288
+co	 287
+_r	 287
+ere	 286
+ce	 284
+tr	 280
+re_	 278
+ent	 275
+x	 275
+ct	 274
+ve	 271
+ru	 259
+ul	 256
+me	 255
+ui	 255
+c_	 252
+_o	 250
+ic	 249
+ns	 247
+_qu	 242
+_q	 242
+no	 241
+ant	 235
+am_	 235
+_co	 233
+sa	 231
+ca	 230
+t,	 226
+mu	 225
+t,_	 225
+_re	 223
+el	 222
+ib	 222
+id	 218
+om	 212
+_te	 211
+al	 209
+le	 209
+it_	 208
+mo	 208
+ol	 206
+_u	 203
+;	 199
+_h	 199
+ac	 198
+;_	 198
+bu	 197
+nu	 196
+ua	 195
+n_	 195
+ll	 194
+tis	 191
+A	 189
+rt	 188
+ge	 188
+nd	 187
+au	 187
+lu	 186
+iu	 185
+squ	 185
+per	 185
+sq	 185
+ter	 185
+pa	 183
+_A	 183
+em_	 183
+ia_	 180
+ed	 179
+_pe	 178
+m,	 176
+sque	 175
+_su	 175
+ae_	 175
+m,_	 175
+pr	 175
+bi	 175
+bus	 174
+_vi	 174
+os_	 173
+ta_	 172
+mqu	 171
+mq	 171
+ss	 170
+sque_	 169
+ibu	 167
+ad	 166
+ibus	 165
+I	 164
+nte	 163
+ra_	 163
+mque	 162
+_de	 162
+po	 161
+_se	 160
+ere_	 160
+nc	 160
+qua	 159
+T	 159
+lo	 157
+oc	 156
+mque_	 156
+_T	 155
+_pa	 155
+_pr	 155
+tem	 154
+bus_	 152
+nti	 149
+rum	 149
+er_	 149
+ab	 148
+ir	 148
+da	 147
+_ve	 146
+ibus_	 146
+ex	 146
+ut	 145
+pi	 145
+tur	 145
+_ca	 143
+_me	 142
+es_	 142
+gi	 142
+te_	 141
+_I	 141
+vo	 141
+do	 141
+_si	 140
+tus	 139
+il	 137
+_ar	 136
+du	 133
+nt_	 133
+uc	 133
+fa	 132
+as_	 132
+rr	 131
+ba	 130
+_ad	 128
+ne_	 127
+_ma	 127
+ens	 127
+gn	 126
+s.	 126
+y	 126
+min	 125
+ris	 124
+in_	 123
+tum	 123
+P	 123
+_g	 123
+mp	 123
+e,	 122
+io	 122
+_P	 122
+ea	 122
+hi	 122
+e,_	 121
+era	 120
+sc	 120
+_la	 120
+qui	 120
+unt	 120
+fe	 119
+_in_	 118
+_no	 118
+ore	 118
+iam	 118
+va	 117
+tis_	 117
+s._	 117
+at_	 117
+eri	 116
+d_	 116
+con	 115
+fu	 115
+pu	 114
+cum	 114
+ub	 114
+ng	 114
+ine	 113
+_au	 113
+:	 113
+_di	 112
+ag	 111
+_con	 111
+ect	 111
+i,	 111
+equ	 111
+i,_	 111
+be	 111
+eq	 111
+_po	 110
+so	 110
+:_	 110
+nis	 109
+ha	 109
+uo	 109
+_fa	 108
+na_	 107
+ip	 107
+is,	 107
+_cu	 106
+cr	 106
+ate	 105
+is,_	 105
+ig	 105
+tor	 105
+rat	 104
+_qua	 103
+eg	 103
+a,	 103
+a,_	 102
+tra	 102
+_mo	 101
+sp	 101
+mis	 100
+itu	 100
+D	 99
+ali	 99
+eb	 99
+eni	 99
+_sa	 98
+ie	 98
+imu	 98
+_ex	 97
+_D	 96
+res	 95
+est	 94
+tri	 94
+ene	 94
+_mi	 94
+str	 94
+enti	 93
+t.	 92
+av	 92
+_per	 91
+ur_	 91
+ora	 91
+lt	 91
+umqu	 90
+_vo	 90
+umq	 90
+up	 89
+t._	 88
+quo	 88
+_ne	 88
+gen	 88
+rum_	 87
+tqu	 87
+tq	 87
+_fu	 86
+ep	 86
+ma_	 86
+umque	 86
+it,_	 85
+ine_	 85
+it,	 85
+men	 85
+mus	 84
+ort	 83
+ven	 83
+ina	 83
+us,_	 83
+us,	 83
+tque	 82
+_ge	 82
+per_	 82
+mor	 82
+inc	 82
+are	 81
+tus_	 81
+_an	 81
+rim	 81
+tque_	 81
+ot	 81
+ani	 80
+H	 80
+_tu	 80
+ho	 80
+tem_	 80
+u_	 80
+ser	 79
+um,_	 79
+um,	 79
+S	 79
+ten	 79
+ver	 79
+sti	 79
+ntu	 78
+fer	 78
diff --git a/libtextcat/data/new_fingerprints/lm/latvian.lm b/libtextcat/data/new_fingerprints/lm/latvian.lm
new file mode 100644
index 000000000000..bffdd309b9bb
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/latvian.lm
@@ -0,0 +1,400 @@
+_	 24504
+a	 8735
+i	 7353
+s	 6064
+t	 5176
+e	 4390
+r	 4339
+u	 4200
+n	 3422
+â	 3055
+m	 2817
+p	 2755
+k	 2703
+o	 2643
+s_	 2595
+d	 2131
+l	 2035
+j	 1972
+î	 1958
+ie	 1887
+v	 1822
+as	 1530
+u_	 1396
+_p	 1380
+b	 1357
+z	 1311
+ç	 1267
+a_	 1261
+as_	 1217
+.	 1065
+,	 1048
+,_	 1033
+g	 1010
+ar	 970
+ð	 965
+ti	 962
+c	 922
+_a	 876
+ja	 838
+st	 828
+_i	 822
+_v	 805
+pa	 792
+_t	 775
+._	 774
+um	 760
+_k	 749
+â_	 734
+_n	 728
+es	 712
+i_	 706
+at	 703
+is	 695
+_s	 680
+ai	 649
+ta	 635
+an	 631
+ka	 621
+r_	 615
+îb	 586
+ij	 585
+_u	 568
+_pa	 548
+un	 541
+no	 539
+va	 537
+ma	 525
+ra	 522
+ri	 515
+iz	 512
+in	 509
+vi	 508
+pr	 506
+sa	 487
+ju	 486
+tâ	 483
+ik	 473
+n_	 472
+am	 454
+en	 452
+tie	 440
+na	 432
+ða	 430
+tu	 420
+ija	 420
+ir	 419
+o_	 415
+m_	 414
+li	 411
+ci	 409
+ku	 404
+mi	 401
+_no	 398
+ek	 398
+_un	 397
+t_	 395
+_l	 394
+un_	 393
+_d	 393
+ot	 392
+_un_	 392
+ies	 391
+ar_	 388
+nâ	 387
+da	 387
+ei	 385
+em	 382
+_ti	 382
+pi	 380
+al	 368
+ba	 356
+ts	 355
+_iz	 353
+ap	 350
+jas	 349
+ko	 346
+au	 345
+ðan	 339
+re	 339
+ni	 337
+kâ	 328
+ro	 327
+et	 326
+rî	 325
+ga	 323
+mu	 322
+jas_	 321
+tr	 317
+_va	 312
+te	 310
+_pr	 307
+sp	 298
+sk	 297
+ne	 295
+îba	 293
+âs	 289
+ijas	 287
+_ar	 283
+la	 283
+to	 282
+ad	 280
+dz	 278
+îg	 277
+tî	 277
+çj	 277
+_sa	 277
+jâ	 274
+_m	 273
+ties	 273
+lî	 272
+ijas_	 269
+_at	 269
+ed	 267
+_pi	 267
+ò	 267
+s,	 265
+s,_	 265
+çr	 261
+gu	 258
+f	 258
+si	 257
+mâ	 256
+nt	 254
+tu_	 254
+_r	 253
+ru	 252
+âj	 251
+jum	 251
+âs_	 250
+ât	 249
+iem	 248
+_b	 248
+_vi	 245
+par	 244
+pie	 244
+rt	 243
+vç	 242
+_ne	 240
+âr	 240
+ai_	 239
+_.	 239
+_j	 237
+us	 237
+_ka	 236
+er	 232
+bas	 232
+_tie	 232
+_par	 230
+di	 229
+û	 228
+ms	 228
+âd	 226
+îbas	 224
+om	 220
+bu	 219
+umu	 217
+iek	 216
+kt	 216
+it	 216
+râ	 215
+_ko	 214
+ana	 211
+âk	 211
+or	 210
+de	 210
+inâ	 207
+dî	 204
+ur	 203
+pri	 203
+_c	 202
+ta_	 202
+bas_	 201
+es_	 201
+_pie	 200
+il	 200
+os	 199
+ðana	 199
+id	 198
+L	 198
+_ie	 197
+bi	 194
+ak	 194
+ja_	 194
+îbas_	 193
+çt	 192
+îbu	 192
+_g	 191
+ï	 189
+ma_	 189
+ien	 188
+kum	 187
+	 187
+_ir	 186
+on	 186
+_ties	 185
+zî	 185
+ce	 185
+ied	 184
+ist	 183
+ts_	 183
+_	 183
+_	 182
+âm	 181
+vie	 180
+__	 180
+cij	 180
+ka_	 179
+_ap	 175
+sî	 174
+ir_	 174
+zi	 174
+uma	 173
+âl	 172
+_ir_	 172
+oð	 171
+_da	 169
+î_	 168
+arî	 168
+)	 167
+do	 166
+ve	 166
+(	 165
+ls	 165
+bu_	 164
+val	 164
+mu_	 164
+isk	 163
+uz	 161
+av	 160
+par_	 160
+_vç	 159
+_par_	 158
+vçr	 158
+_ar_	 157
+rie	 157
+_uz	 157
+aj	 156
+îbu_	 156
+oj	 155
+kâ_	 155
+ld	 154
+iet	 154
+iku	 154
+ks	 153
+du	 153
+ep	 153
+ms_	 152
+ec	 152
+V	 151
+ais	 150
+str	 150
+nie	 149
+am_	 149
+ums	 148
+_(	 147
+ju_	 146
+z_	 142
+ru_	 142
+îj	 142
+gum	 142
+u,_	 141
+u,	 141
+iò	 141
+uma_	 141
+çrt	 141
+îgu	 141
+me	 140
+dâ	 140
+ît	 140
+ent	 139
+ikum	 138
+pâ	 138
+em_	 138
+_L	 138
+lie	 136
+sta	 136
+rî_	 136
+lst	 136
+eik	 135
+se	 135
+s.	 134
+pro	 134
+rs	 134
+s._	 134
+tik	 134
+lç	 134
+ska	 133
+pap	 133
+kas	 133
+rm	 133
+âju	 133
+pî	 132
+nu	 132
+T	 132
+pç	 131
+tei	 131
+nas	 131
+_V	 131
+jo	 131
+lîg	 131
+ut	 131
+iem_	 130
+ras	 129
+pu	 129
+_li	 129
+_ga	 128
+dar	 128
+_kâ	 128
+umu_	 127
+îv	 126
+îgum	 126
+kas_	 126
+tîb	 125
+vai	 125
+lîgu	 125
+P	 125
+arî_	 125
+ev	 124
+lai	 124
+îr	 124
+lîgum	 124
+tv	 123
+að	 123
+_arî_	 122
+_arî	 122
+_vie	 121
+S	 121
+_T	 120
+îju	 120
+teik	 120
+cija	 119
+rb	 119
+_ð	 119
+jâ_	 119
+nas_	 118
+tâj	 118
+vçrt	 118
+iec	 118
+_la	 117
+îd	 116
+_vai	 116
+îjum	 116
+vien	 116
+als	 116
+_lî	 116
+apîr	 115
+rts	 115
+isi	 115
+pîr	 115
+papî	 115
+papîr	 115
+apî	 115
+tsp	 115
+mç	 114
+im	 114
+be	 114
+is_	 114
+alst	 114
+_ja	 114
+rtspa	 113
diff --git a/libtextcat/data/new_fingerprints/lm/lithuanian.lm b/libtextcat/data/new_fingerprints/lm/lithuanian.lm
new file mode 100644
index 000000000000..eca25a45b2ba
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/lithuanian.lm
@@ -0,0 +1,400 @@
+_	 23070
+i	 8196
+a	 7763
+s	 5179
+e	 3458
+o	 3425
+u	 3371
+t	 3344
+r	 3240
+n	 3070
+k	 3019
+l	 2060
+p	 1889
+s_	 1756
+m	 1680
+d	 1640
+v	 1590
+,	 1501
+,_	 1497
+ó	 1400
+g	 1302
+j	 1200
+o_	 1138
+.	 1128
+ai	 1113
+÷	 1075
+_p	 1047
+_k	 1035
+i_	 990
+._	 984
+as	 975
+b	 937
+au	 903
+is	 863
+_n	 815
+ka	 811
+si	 804
+_s	 799
+ia	 796
+ý	 759
+ta	 735
+ie	 731
+ti	 728
+y	 721
+_t	 711
+in	 697
+_i	 686
+us	 675
+pa	 658
+ir	 640
+ar	 633
+ù	 620
+_a	 617
+r_	 609
+ne	 583
+a_	 578
+ri	 569
+_v	 558
+_pa	 541
+al	 540
+ra	 531
+li	 522
+Ý	 509
+u_	 493
+vi	 490
+_ka	 489
+da	 487
+_ne	 482
+_j	 481
+en	 478
+ù_	 445
+os	 444
+ki	 442
+õ	 441
+an	 440
+ik	 434
+ma	 433
+as_	 430
+st	 420
+_d	 420
+ai_	 417
+s,_	 396
+am	 396
+is_	 396
+s,	 396
+_ir	 390
+jo	 387
+ir_	 385
+at	 384
+_ir_	 383
+i÷	 381
+ni	 377
+ga	 376
+_b	 367
+na	 366
+e_	 365
+to	 352
+pr	 337
+_g	 332
+_m	 332
+û	 328
+ß	 326
+io	 323
+ei	 323
+Ý_	 321
+su	 320
+ßi	 320
+uo	 319
+la	 317
+er	 303
+va	 299
+vo	 298
+ýi	 293
+es	 291
+-	 290
+ó_	 286
+-_	 285
+_vi	 284
+_-	 283
+ko	 283
+_-_	 283
+iau	 281
+sa	 278
+s.	 278
+iu	 276
+et	 274
+nu	 265
+ja	 262
+õ_	 262
+_ta	 262
+s._	 259
+el	 258
+ój	 258
+os_	 256
+im	 255
+it	 254
+_pr	 253
+no	 252
+av	 251
+ur	 251
+_÷	 248
+mi	 246
+ve	 245
+ak	 245
+ku	 243
+ek	 241
+tu	 241
+_ý	 241
+ad	 241
+ñ	 238
+_l	 238
+_i÷	 236
+us_	 236
+_su	 232
+oj	 231
+au_	 231
+ba	 224
+nt	 218
+me	 214
+te	 210
+jo_	 208
+ro	 205
+ós	 204
+iù	 203
+tai	 203
+_õ	 201
+ló	 201
+pas	 200
+ip	 198
+iai	 197
+di	 195
+usi	 194
+vo_	 193
+kai	 190
+i,	 189
+i,_	 189
+sk	 187
+_r	 186
+aus	 184
+ap	 183
+gi	 182
+mo	 182
+uk	 181
+t_	 180
+_da	 177
+be	 176
+ien	 176
+o,	 174
+il	 174
+o,_	 173
+ti_	 173
+re	 172
+_nu	 171
+ßia	 171
+_pas	 169
+pri	 169
+÷_	 169
+ok	 168
+dó	 166
+ól	 162
+bu	 161
+÷i	 160
+on	 160
+asi	 159
+id	 158
+ul	 157
+ji	 157
+aip	 156
+ia_	 155
+_sa	 154
+ot	 154
+gal	 153
+nk	 153
+om	 152
+p_	 151
+_pri	 151
+od	 151
+vis	 150
+_at	 150
+vie	 150
+uv	 150
+ab	 150
+iù_	 149
+ama	 149
+nó	 149
+A	 149
+sta	 148
+kr	 148
+_A	 145
+ais	 144
+rt	 143
+J	 142
+_J	 142
+ójo	 142
+_õ_	 141
+K	 140
+_K	 139
+pi	 139
+avo	 139
+ng	 139
+mas	 138
+du	 138
+ug	 137
+_ga	 137
+ol	 136
+tik	 135
+ali	 135
+..	 135
+_vis	 135
+iek	 134
+ini	 133
+kad	 133
+a,	 133
+le	 133
+kó	 133
+T	 133
+tó	 132
+i.	 132
+_T	 131
+dý	 131
+a,_	 131
+go	 131
+ip_	 131
+aip_	 131
+ró	 129
+a÷	 129
+dýi	 129
+ke	 128
+k_	 128
+d_	 127
+ad_	 127
+_ti	 127
+_ma	 126
+_va	 125
+i._	 124
+z	 123
+÷k	 123
+iau_	 121
+m_	 120
+kar	 119
+um	 119
+tù	 119
+_kad	 118
+uý	 117
+tr	 117
+_kai	 117
+as,	 116
+og	 116
+kad_	 116
+as,_	 116
+_ji	 116
+rie	 115
+yt	 114
+_ja	 114
+_ko	 114
+vó	 114
+ys	 114
+jau	 113
+ar_	 113
+pra	 112
+aý	 112
+ant	 112
+kl	 111
+tas	 111
+gu	 111
+_ku	 110
+si_	 110
+pe	 109
+eb	 109
+N	 109
+ójo_	 108
+_kad_	 108
+se	 108
+_ki	 108
+or	 107
+ly	 107
+lo	 107
+iai_	 107
+_la	 106
+ts	 106
+ñs	 106
+ig	 105
+_N	 105
+ut	 105
+_u	 105
+ós_	 105
+avo_	 104
+ie_	 104
+a.	 104
+kt	 104
+em	 103
+do	 103
+je	 102
+ks	 102
+ats	 101
+_be	 101
+ris	 101
+l_	 101
+_vie	 101
+tin	 101
+ag	 100
+dam	 100
+_st	 100
+a._	 99
+_bu	 99
+?	 99
+V	 98
+io_	 98
+kas	 98
+_jo	 98
+vien	 97
+_gal	 97
+ót	 97
+kia	 97
+lia	 96
+c	 96
+uri	 96
+_V	 96
+?_	 96
+uvo	 95
+ru	 95
+ty	 95
+ep	 94
+nd	 94
+lai	 94
+_tai	 94
+ju	 93
+man	 92
+o.	 92
+buv	 92
+tÝ	 92
+_÷i	 91
+i÷_	 91
+_i÷_	 91
+i÷k	 90
+o._	 90
+_to	 90
+bi	 90
+up	 89
+po	 89
+rs	 89
+_prie	 88
+ù,_	 88
+aik	 88
+ui	 88
+_tik	 88
+ij	 88
+ù,	 88
+pat	 88
+prie	 88
+I	 87
+ies	 87
+tai_	 87
+n_	 87
+pasi	 87
+ius	 87
+÷t	 87
+eik	 86
+_me	 86
+ina	 86
diff --git a/libtextcat/data/new_fingerprints/lm/malay.lm b/libtextcat/data/new_fingerprints/lm/malay.lm
new file mode 100644
index 000000000000..911d0cfef150
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/malay.lm
@@ -0,0 +1,400 @@
+_	 87128
+a	 50232
+n	 25424
+e	 18746
+i	 18605
+an	 14419
+u	 12470
+k	 11955
+t	 11875
+r	 11007
+d	 9856
+g	 9545
+m	 9390
+s	 8926
+l	 8631
+n_	 8004
+an_	 7095
+p	 6890
+a_	 6739
+b	 6645
+ng	 6630
+h	 5964
+da	 5153
+_d	 5107
+er	 4625
+ka	 4448
+la	 4339
+y	 4323
+i_	 4295
+en	 4159
+ya	 3800
+ang	 3778
+_m	 3750
+o	 3593
+.	 3539
+._	 3310
+at	 3288
+ah	 3216
+_b	 3199
+_s	 3177
+ta	 3076
+ra	 3036
+_k	 2949
+g_	 2939
+ng_	 2933
+ar	 2915
+_p	 2906
+me	 2884
+ga	 2781
+di	 2778
+ak	 2727
+al	 2705
+_me	 2671
+ang_	 2524
+h_	 2509
+ba	 2508
+pa	 2454
+kan	 2449
+in	 2437
+tu	 2411
+_t	 2376
+sa	 2338
+_da	 2276
+j	 2276
+pe	 2225
+,	 2150
+k_	 2147
+ma	 2143
+se	 2138
+am	 2131
+kan_	 2117
+_di	 2082
+,_	 2079
+ke	 2048
+un	 2004
+be	 1947
+_a	 1925
+na	 1871
+ti	 1868
+ri	 1861
+u_	 1857
+as	 1854
+ny	 1827
+ha	 1789
+te	 1788
+_pe	 1768
+em	 1750
+it	 1737
+_i	 1732
+_ke	 1711
+yan	 1706
+ad	 1698
+ia	 1673
+yang	 1673
+_y	 1668
+_ya	 1655
+yang_	 1653
+_se	 1648
+ah_	 1646
+_yan	 1639
+_yang	 1639
+ala	 1612
+nya	 1587
+el	 1576
+ik	 1571
+t_	 1568
+ai	 1549
+men	 1531
+eng	 1522
+_men	 1464
+nga	 1441
+dan	 1366
+_be	 1365
+si	 1343
+uk	 1328
+ada	 1299
+nt	 1291
+__	 1287
+ap	 1276
+ua	 1265
+___	 1238
+-	 1213
+ja	 1211
+ber	 1204
+gan	 1203
+_ba	 1193
+____	 1189
+ni	 1181
+_te	 1169
+c	 1143
+ran	 1141
+_____	 1140
+m_	 1127
+ara	 1118
+per	 1099
+le	 1084
+_dan	 1083
+dan_	 1079
+ngan	 1060
+_dan_	 1050
+ya_	 1046
+at_	 1044
+da_	 1021
+li	 1016
+aka	 1013
+A	 999
+r_	 999
+w	 997
+eb	 995
+lah	 980
+ata	 980
+ak_	 978
+nd	 974
+_ber	 955
+gi	 936
+is	 933
+il	 931
+tu_	 923
+s_	 920
+gan_	 915
+mb	 913
+wa	 904
+ag	 903
+ngan_	 898
+ter	 887
+nya_	 877
+S	 873
+ek	 853
+ru	 852
+_l	 838
+ela	 828
+itu	 824
+ol	 822
+aha	 822
+ada_	 820
+pu	 812
+di_	 807
+bu	 807
+am_	 804
+ur	 801
+tan	 790
+mp	 790
+_per	 786
+_sa	 784
+M	 782
+ut	 781
+us	 779
+era	 779
+lam	 778
+lah_	 775
+asa	 767
+ki	 761
+ir	 759
+de	 756
+enga	 750
+su	 748
+du	 741
+id	 739
+"	 733
+akan	 732
+apa	 728
+_S	 724
+ul	 721
+lu	 717
+ari	 717
+dal	 704
+et	 698
+es	 698
+pad	 688
+_ma	 688
+_M	 685
+ana	 684
+bi	 679
+pada	 673
+dala	 673
+l_	 671
+ep	 664
+f	 662
+_di_	 658
+B	 655
+ing	 655
+_j	 654
+ika	 653
+ku	 650
+_.	 644
+akan_	 642
+ama	 637
+pen	 636
+alam	 634
+eh	 634
+pada_	 633
+ai_	 632
+_ter	 632
+K	 631
+mu	 628
+ju	 628
+P	 626
+mem	 625
+au	 622
+_mem	 614
+lan	 612
+_._	 611
+ntu	 608
+lam_	 605
+um	 601
+on	 600
+gk	 597
+_in	 597
+ngk	 597
+a.	 584
+meng	 582
+_meng	 578
+alam_	 577
+_A	 576
+aa	 575
+uk_	 572
+_pen	 569
+ban	 569
+or	 569
+st	 566
+ay	 566
+dar	 565
+_pa	 564
+a._	 564
+_h	 562
+bah	 562
+_P	 560
+D	 559
+ri_	 558
+ini	 552
+_de	 551
+rt	 550
+aan	 545
+_it	 542
+_itu	 542
+nda	 540
+eri	 540
+dalam	 537
+_B	 533
+_dal	 532
+ip	 532
+_dala	 532
+ta_	 528
+_u	 527
+ung	 525
+ih	 524
+aw	 520
+_n	 519
+atu	 517
+ila	 513
+mi	 513
+leh	 513
+ian	 512
+tuk	 509
+awa	 508
+gu	 506
+ert	 506
+engan	 505
+ole	 504
+_K	 501
+seb	 497
+ca	 496
+gg	 493
+_ta	 489
+ra_	 488
+ngg	 488
+itu_	 487
+emb	 482
+ni_	 482
+ida	 482
+nj	 482
+_ti	 479
+man	 478
+den	 477
+_D	 474
+_ka	 473
+aj	 470
+oleh	 468
+n.	 468
+n._	 464
+ngka	 464
+gka	 464
+dak	 464
+anga	 461
+ena	 459
+san	 458
+pat	 458
+rk	 458
+(	 455
+ent	 454
+agi	 453
+)	 451
+ia_	 450
+ge	 450
+ab	 449
+im	 447
+_ini	 446
+ntuk	 445
+I	 445
+ar_	 440
+N	 439
+aan_	 436
+_la	 433
+pi	 432
+baha	 431
+deng	 430
+han	 430
+bag	 429
+eh_	 429
+hu	 429
+denga	 428
+_o	 427
+na_	 427
+T	 425
+leh_	 422
+_den	 422
+ka_	 419
+any	 415
+ud	 415
+rang	 414
+anya	 413
+gi_	 412
+angan	 412
+a,	 411
+_deng	 410
+ita	 409
+kat	 408
+re	 408
+_(	 406
+tuk_	 403
+aga	 401
+ne	 400
+and	 399
+aya	 398
+_dar	 397
+a,_	 396
+ro	 396
+ntuk_	 393
+eba	 392
+aran	 390
+_"	 387
+ed	 385
+end	 384
+ko	 383
+sa_	 381
+p_	 381
+ara_	 380
+_seb	 379
+alah	 379
+oleh_	 379
+an.	 378
+dak_	 378
+eg	 378
+hi	 376
+dari	 375
+an._	 375
+au_	 373
+bo	 373
+ti_	 371
+ula	 371
diff --git a/libtextcat/data/new_fingerprints/lm/manx_gaelic.lm b/libtextcat/data/new_fingerprints/lm/manx_gaelic.lm
new file mode 100644
index 000000000000..e6eceebeb080
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/manx_gaelic.lm
@@ -0,0 +1,400 @@
+_	 36004
+e	 9455
+a	 8302
+y	 6395
+n	 6395
+h	 5736
+r	 4939
+s	 4799
+o	 4429
+i	 4129
+l	 3462
+y_	 2896
+g	 2731
+n_	 2549
+d	 2232
+t	 2160
+_a	 1836
+m	 1823
+sh	 1774
+e_	 1746
+h_	 1645
+yn	 1550
+c	 1531
+ee	 1515
+gh	 1461
+s_	 1460
+_s	 1388
+ey	 1345
+_e	 1316
+ag	 1312
+a_	 1201
+r_	 1173
+agh	 1165
+in	 1148
+as	 1136
+_d	 1136
+u	 1124
+he	 1060
+yn_	 1025
+oo	 1012
+ey_	 1005
+_m	 1002
+er	 965
+v	 949
+_y	 941
+_v	 895
+_c	 891
+_as	 880
+'	 869
+,	 866
+_n	 832
+ll	 828
+,_	 827
+_sh	 818
+.	 802
+hi	 797
+as_	 770
+ee_	 768
+ne	 767
+_as_	 764
+b	 762
+re	 735
+ay	 730
+._	 730
+an	 726
+ar	 725
+gh_	 722
+ny	 709
+en	 703
+_r	 697
+ch	 688
+agh_	 687
+dy	 686
+t_	 677
+le	 667
+k	 658
+er_	 616
+oi	 612
+ea	 607
+_t	 601
+yr	 596
+_er	 585
+ra	 574
+_dy	 572
+in_	 570
+l_	 564
+f	 557
+_l	 556
+ha	 551
+_g	 548
+_ny	 534
+nn	 530
+"	 528
+_ch	 527
+_y_	 524
+ie	 514
+dy_	 514
+_dy_	 513
+aa	 510
+_f	 509
+j	 504
+sh_	 487
+oa	 480
+is	 478
+_h	 470
+rr	 468
+ny_	 467
+_ny_	 463
+_er_	 454
+ish	 445
+ho	 442
+ai	 441
+d_	 435
+ro	 423
+ht	 418
+ei	 417
+shi	 416
+il	 409
+me	 408
+_ay	 403
+_b	 403
+la	 400
+_j	 400
+my	 394
+va	 391
+ns	 386
+on	 385
+_o	 381
+ys	 380
+_shi	 379
+ia	 377
+ayn	 373
+_va	 371
+hen	 362
+she	 356
+ri	 345
+lle	 342
+ooi	 342
+mee	 340
+ley	 335
+_me	 331
+el	 330
+rt	 328
+ie_	 327
+eh	 324
+w	 316
+_ayn	 313
+al	 311
+g_	 309
+ish_	 308
+lley	 307
+mee_	 305
+_mee	 304
+ill	 301
+es	 299
+na	 299
+je	 298
+yns	 296
+C	 294
+_my	 291
+_she	 290
+ley_	 282
+V	 280
+_yn	 278
+_"	 278
+_mee_	 277
+ta	 272
+_V	 271
+ys_	 268
+-	 268
+lley_	 265
+hin	 264
+_ro	 259
+shin	 256
+_yn_	 255
+_je	 255
+do	 253
+va_	 253
+ne_	 253
+_va_	 252
+ns_	 252
+_shin	 251
+yns_	 250
+ayns	 248
+en_	 247
+che	 246
+_ayns	 246
+eh_	 246
+_do	 242
+ad	 241
+ney	 240
+o_	 240
+ym	 240
+ed	 239
+yr_	 239
+ayns_	 237
+ur	 237
+st	 234
+_C	 234
+rt_	 234
+'n	 232
+m_	 232
+p	 231
+li	 231
+or	 230
+ow	 228
+hin_	 225
+da	 225
+shen	 223
+"_	 223
+'n_	 223
+Va	 221
+ght	 220
+shin_	 219
+tr	 217
+_Va	 217
+ry	 216
+ve	 216
+_shen	 215
+ty	 214
+mo	 206
+_'	 205
+_ve	 205
+ma	 203
+be	 203
+te	 203
+hie	 203
+hey	 203
+nag	 202
+ll_	 201
+yl	 200
+w_	 200
+ss	 200
+aa_	 198
+nagh	 198
+an_	 197
+io	 195
+ow_	 194
+it	 194
+sy	 193
+ayr	 193
+ney_	 192
+E	 192
+sht	 192
+ni	 191
+_k	 190
+ha_	 190
+ain	 189
+u_	 189
+hy	 189
+aght	 188
+oo_	 188
+ree	 188
+lh	 187
+_tr	 186
+esh	 186
+_che	 183
+yrt	 182
+_da	 182
+oar	 182
+doo	 181
+k_	 181
+se	 180
+au	 180
+ille	 179
+ar_	 179
+_lh	 179
+ki	 177
+arr	 176
+ec	 176
+ol	 175
+_doo	 175
+T	 175
+row	 175
+_row	 174
+ge	 173
+so	 172
+oy	 171
+oil	 170
+_re	 170
+_ag	 170
+'e	 169
+rey	 169
+illey	 169
+ck	 168
+ad_	 168
+ann	 168
+n,	 166
+eea	 166
+_ta	 166
+ht_	 165
+ae	 162
+_row_	 162
+!	 162
+row_	 162
+ane	 161
+fe	 161
+dd	 160
+go	 159
+tyn	 159
+oin	 158
+ooa	 158
+n.	 158
+eg	 156
+_ec	 156
+_ma	 156
+_agh	 155
+n,_	 154
+_fe	 154
+Ch	 154
+nyn	 153
+fo	 152
+eay	 152
+nagh_	 152
+n._	 152
+_go	 151
+S	 150
+ke	 150
+hey_	 150
+enn	 150
+cha	 149
+rre	 149
+_fo	 149
+ghe	 149
+raa	 149
+G	 148
+lan	 148
+mm	 147
+ym_	 147
+A	 146
+c_	 146
+oill	 145
+hee	 144
+ooar	 144
+_E	 144
+nne	 143
+tey	 142
+ir	 141
+de	 141
+hyn	 140
+_he	 140
+nyn_	 140
+'s	 139
+_gh	 139
+_cha	 138
+L	 138
+yrt_	 138
+_Ch	 137
+e,	 137
+lla	 136
+Va_	 136
+ooin	 136
+ell	 135
+a'	 135
+os	 135
+_oo	 134
+am	 134
+rish	 133
+th	 133
+_mo	 133
+ris	 133
+iag	 133
+gg	 133
+_Va_	 132
+iagh	 132
+_G	 132
+e,_	 132
+ass	 132
+!_	 132
+my_	 132
+hoo	 131
+_T	 131
+nee	 130
+a'n_	 129
+rag	 129
+a'n	 129
+_'s	 129
+_so	 128
+co	 128
+rey_	 128
+_eh	 126
+_my_	 126
+nni	 126
+ou	 126
+_'sy	 125
+'sy	 125
+_p	 125
+vo	 125
+_S	 125
+H	 125
+_agh_	 125
+tra	 124
+moo	 124
+hu	 123
+ooy	 123
+ragh	 123
+al_	 123
+it_	 123
+hia	 122
+id	 122
diff --git a/libtextcat/data/new_fingerprints/lm/marathi.lm b/libtextcat/data/new_fingerprints/lm/marathi.lm
new file mode 100644
index 000000000000..479f4fd9b760
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/marathi.lm
@@ -0,0 +1,400 @@
+�	 17815
+_	 14534
+��	 4035
+�_	 3087
+�	 2180
+�	 1762
+��	 1669
+�	 1654
+�	 1534
+�	 1480
+��	 1433
+�	 1342
+�	 1289
+�	 1237
+�	 1163
+�	 1158
+�	 1153
+��_	 1133
+�	 1099
+�	 1084
+�	 1062
+�	 1059
+�_	 1054
+��	 1054
+��	 1050
+���	 1039
+��	 989
+�	 983
+��	 968
+�	 965
+�	 949
+_�	 936
+.	 936
+��	 915
+��	 859
+��	 842
+��	 838
+��	 836
+��	 769
+��	 764
+�	 710
+��	 710
+��	 684
+���	 681
+._	 670
+��_	 637
+�	 609
+��	 578
+_�	 578
+_��	 569
+_�	 543
+��	 530
+_�	 530
+��	 524
+_�	 523
+�	 511
+�	 504
+�_	 495
+��_	 477
+���	 476
+��	 474
+_�	 474
+_�	 457
+_��	 447
+_��	 447
+���_	 446
+��	 444
+�	 438
+��	 423
+���	 422
+��	 409
+��	 388
+��	 387
+���	 381
+�_	 366
+���	 359
+�	 339
+���	 334
+_��	 332
+��	 331
+��	 324
+���	 320
+_��	 320
+���	 318
+�	 315
+_�	 315
+��_	 314
+�	 313
+��	 306
+��_	 303
+��	 301
+��	 297
+�	 297
+���	 295
+��	 284
+��	 280
+�	 274
+�_	 272
+���	 270
+���	 268
+���_	 268
+��	 264
+��	 264
+��	 263
+,	 258
+����	 256
+����	 256
+���_	 256
+,_	 255
+���	 255
+�	 249
+���	 247
+���	 243
+���	 241
+_�	 234
+_��	 233
+���	 232
+��	 232
+��	 231
+��_	 231
+���	 230
+���	 228
+�	 227
+�	 226
+���	 225
+�_	 223
+���	 221
+��	 220
+_�	 220
+��	 219
+��_	 218
+���	 217
+�.	 216
+��	 215
+_��	 213
+..	 209
+_���	 209
+����	 205
+���	 205
+����	 204
+�	 204
+���	 203
+����_	 202
+�_	 202
+���	 201
+�	 198
+_�	 198
+��	 193
+_�	 191
+���	 190
+�._	 189
+���	 188
+��	 188
+����	 187
+�	 186
+��	 186
+�	 185
+��_	 180
+��_	 180
+_��	 180
+��	 179
+�	 178
+_���	 176
+_���	 175
+_����	 175
+��	 175
+_��	 175
+���	 174
+���	 171
+��	 170
+_�	 170
+...	 168
+���	 167
+���	 166
+_�	 164
+���	 164
+���	 163
+����	 163
+��	 162
+���	 162
+_���	 162
+����_	 161
+��	 160
+��_	 159
+����	 159
+���	 157
+���	 154
+��	 154
+_��	 154
+_�	 154
+��	 153
+���	 153
+��	 151
+���	 151
+_�	 151
+����	 150
+��	 150
+��	 150
+�.	 149
+_����	 149
+��	 148
+���	 148
+��	 147
+��	 147
+ţ	 146
+���_	 146
+_��	 145
+�._	 145
+���	 144
+��	 143
+�	 142
+�	 140
+����	 140
+���	 139
+��	 139
+���	 137
+���	 136
+_��	 136
+��	 136
+_��	 135
+�.	 135
+���	 135
+'	 135
+�ţ	 134
+_��	 132
+����	 131
+����_	 131
+���	 129
+'_	 129
+_���	 129
+�._	 128
+��	 127
+....	 127
+�	 127
+��	 126
+���	 125
+_��	 124
+��_	 123
+����	 123
+�	 122
+;	 122
+_��	 121
+_���	 119
+�	 118
+���	 115
+���	 114
+��_	 114
+���	 113
+����	 113
+���	 113
+b	 113
+���	 112
+_'	 112
+s	 111
+&	 111
+���	 111
+���	 111
+����	 111
+p	 111
+�	 111
+_�	 110
+�����	 110
+bs	 109
+��	 109
+n	 109
+�	 109
+_���	 108
+&n	 107
+bsp;	 107
+nbsp;	 107
+sp;	 107
+nb	 107
+bsp	 107
+nbs	 107
+sp	 107
+nbsp	 107
+&nb	 107
+&nbsp	 107
+p;	 107
+&nbs	 107
+����	 106
+_'_	 106
+���	 106
+���	 106
+���	 106
+���_	 105
+���	 104
+���	 104
+��	 104
+��	 104
+_��	 103
+����	 103
+��	 103
+���	 102
+����	 101
+����	 100
+����	 99
+�,	 99
+_�	 98
+�,_	 98
+_�ţ	 98
+���	 98
+����_	 98
+_���	 97
+;&	 97
+_���	 97
+����	 97
+_����	 96
+��	 96
+�����	 96
+���	 96
+�	 96
+;&nb	 95
+p;&nb	 95
+;&n	 95
+p;&	 95
+;&nbs	 95
+bsp;&	 95
+.....	 95
+��_	 95
+sp;&n	 95
+sp;&	 95
+p;&n	 95
+�	 94
+_�	 94
+�	 94
+����_	 94
+����	 93
+���	 93
+���_	 93
+��_	 93
+���	 93
+_�	 92
+��	 92
+_���	 92
+���_	 92
+���	 92
+���_	 91
+��	 91
+��_	 90
+_���	 90
+_���	 90
+�����	 90
+�	 90
+����	 90
+��	 89
+��	 89
+����	 89
+���_	 89
+��	 89
+���	 89
+����	 89
+��	 89
+���	 89
+_��	 88
+��	 88
+�����	 88
+_��	 88
+_���	 88
+����	 87
+��	 87
+��	 87
+�����	 87
+_�	 87
+��	 87
+����	 87
+����	 86
+���_	 86
+_���	 85
+���	 85
+��	 85
+_�	 85
+���	 85
+_����	 84
+��	 84
+����	 83
+���	 83
+���	 83
+��	 83
+���	 83
+���_	 83
+_�	 82
+_����	 82
+����_	 82
+���_	 82
+�����	 82
+����	 82
+���_	 82
+_��	 82
+���_	 82
+���_	 81
+��	 81
+�._	 80
+���	 80
+_���	 80
+�.	 80
+��	 79
+_��	 79
+����_	 79
+�	 79
diff --git a/libtextcat/data/new_fingerprints/lm/middle_frisian.lm b/libtextcat/data/new_fingerprints/lm/middle_frisian.lm
new file mode 100644
index 000000000000..17e4f149d122
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/middle_frisian.lm
@@ -0,0 +1,400 @@
+_	 60524
+e	 20138
+n	 10664
+t	 8674
+i	 7833
+a	 7549
+o	 7278
+r	 6963
+n_	 5391
+s	 5087
+d	 4731
+t_	 4327
+l	 4306
+e_	 4271
+en	 4068
+k	 3483
+m	 3346
+g	 2990
+er	 2965
+en_	 2835
+y	 2597
+w	 2481
+h	 2475
+j	 2441
+_d	 2375
+r_	 2250
+u	 2059
+s_	 1921
+ie	 1780
+_h	 1725
+z	 1710
+de	 1666
+_m	 1652
+_w	 1629
+_i	 1611
+et	 1550
+te	 1540
+b	 1538
+.	 1517
+er_	 1481
+in	 1420
+an	 1408
+p	 1392
+f	 1311
+,	 1280
+,_	 1273
+k_	 1266
+._	 1258
+y_	 1238
+_z	 1230
+oe	 1162
+v	 1144
+et_	 1138
+ne	 1131
+ee	 1125
+st	 1120
+_o	 1107
+_s	 1107
+_e	 1076
+_n	 1068
+_b	 989
+_t	 988
+l_	 983
+oo	 981
+ge	 975
+je	 963
+_g	 952
+at	 949
+me	 946
+ij	 943
+is	 913
+he	 899
+'	 892
+aa	 882
+el	 870
+_v	 864
+re	 843
+ar	 837
+_de	 805
+on	 800
+ke	 796
+de_	 788
+ei	 782
+_a	 776
+_'	 770
+le	 744
+at_	 742
+it	 741
+_k	 738
+or	 734
+an_	 729
+in_	 723
+da	 715
+te_	 703
+_he	 680
+_l	 664
+H	 661
+al	 652
+_H	 652
+a_	 650
+_da	 648
+D	 648
+d_	 646
+_D	 643
+es	 617
+g_	 608
+is_	 606
+æ	 596
+_f	 594
+'t	 591
+_'t	 584
+'t_	 583
+_me	 580
+c	 576
+_'t_	 576
+ri	 571
+_en	 564
+yn	 563
+_en_	 559
+ze	 538
+m_	 535
+om	 535
+ik	 522
+_de_	 522
+ed	 521
+be	 517
+wi	 509
+ch	 509
+ol	 498
+ar_	 498
+ha	 496
+_ne	 495
+we	 494
+ou	 486
+nd	 474
+ma	 474
+ik_	 470
+J	 459
+_ik	 456
+_ik_	 451
+_J	 451
+ll	 450
+M	 446
+li	 443
+wa	 442
+_M	 442
+ien	 435
+ro	 432
+di	 421
+nn	 418
+ste	 415
+wo	 415
+yn_	 415
+_r	 413
+_ha	 411
+it_	 409
+tt	 408
+ve	 407
+S	 404
+_j	 399
+_S	 398
+_in	 395
+as	 395
+der	 395
+hi	 389
+_al	 388
+uw	 384
+tte	 384
+ng	 381
+_wi	 381
+nne	 381
+het	 380
+_het	 378
+lle	 376
+nt	 374
+ns	 373
+op	 373
+je_	 367
+E	 366
+ek	 363
+B	 363
+dat	 362
+_B	 362
+_ma	 362
+_in_	 361
+_dat	 359
+_wo	 359
+ier	 358
+og	 357
+_E	 354
+_ge	 352
+dat_	 349
+ne_	 349
+eer	 349
+het_	 348
+_het_	 348
+_is	 348
+_dat_	 348
+ey	 347
+W	 346
+_W	 343
+_te	 339
+eg	 337
+ra	 335
+rs	 335
+!	 332
+zi	 332
+gt	 329
+_He	 327
+He	 327
+_be	 324
+j_	 320
+ij_	 320
+u_	 319
+f_	 317
+_di	 316
+;	 315
+_we	 315
+_is_	 314
+rt	 313
+!_	 313
+;_	 312
+n.	 311
+p_	 310
+la	 310
+_wa	 310
+ea	 308
+_u	 308
+pe	 304
+ta	 304
+il	 301
+my	 300
+ig	 300
+n,	 300
+n,_	 298
+iet	 297
+sc	 297
+ter	 296
+sch	 296
+oor	 295
+no	 294
+_my	 293
+n._	 291
+ti	 290
+_zi	 289
+st_	 288
+el_	 283
+gen	 282
+se	 280
+K	 279
+_oo	 278
+ui	 278
+e,	 275
+ten	 274
+net	 274
+oon	 274
+ho	 274
+jn	 273
+e,_	 273
+ijn	 272
+ien_	 272
+ko	 272
+N	 271
+ni	 271
+_N	 269
+den	 269
+za	 268
+_net	 267
+i_	 266
+wol	 266
+een	 264
+va	 264
+am	 264
+do	 263
+ol_	 262
+le_	 261
+_te_	 260
+rd	 260
+ke_	 259
+ey_	 259
+ers	 258
+_K	 255
+_ie	 255
+ver	 254
+to	 254
+_hi	 253
+nde	 253
+:	 253
+der_	 252
+jo	 251
+net_	 251
+al_	 250
+_wol	 250
+_p	 250
+_no	 250
+aar	 248
+_za	 245
+_net_	 245
+nk	 242
+est	 241
+om_	 241
+_va	 241
+ak	 241
+tj	 239
+ae	 238
+_op	 237
+mo	 236
+tr	 236
+_st	 233
+ier_	 233
+_ve	 233
+mm	 232
+T	 231
+eu	 229
+_ze	 228
+:_	 228
+mi	 228
+ag	 227
+zo	 227
+_ko	 226
+vo	 225
+_T	 225
+nne_	 225
+F	 224
+..	 224
+fo	 224
+_F	 223
+en,	 223
+oe_	 222
+wie	 222
+en,_	 221
+kk	 221
+_ien	 220
+on_	 218
+wol_	 218
+_fo	 218
+I	 217
+_do	 216
+eit	 214
+ei_	 214
+mme	 214
+G	 213
+_I	 213
+as_	 213
+or_	 211
+A	 211
+_G	 210
+_A	 210
+lle_	 209
+Da	 208
+_Da	 207
+_wol_	 207
+ren	 206
+_ee	 206
+e.	 205
+van	 205
+jen	 205
+een_	 205
+_van	 204
+kke	 204
+en.	 204
+O	 204
+_vo	 204
+V	 203
+_O	 203
+_V	 203
+ken	 203
+_mo	 203
+ot	 202
+ie_	 201
+ou_	 201
+ur	 201
+tte_	 200
+em	 200
+_van_	 199
+L	 199
+van_	 199
+_zo	 199
+op_	 199
+_L	 197
+iet_	 196
+of	 194
+ten_	 194
+oer	 193
+_ien_	 193
+e._	 193
+oed	 192
+hie	 192
+zy	 191
+en._	 191
+De	 191
+_ver	 191
+_ho	 189
+_De	 189
+oa	 189
+den_	 188
+_zy	 188
+lo	 187
+dan	 187
+nt_	 186
diff --git a/libtextcat/data/new_fingerprints/lm/mingo.lm b/libtextcat/data/new_fingerprints/lm/mingo.lm
new file mode 100644
index 000000000000..4d1947a33345
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/mingo.lm
@@ -0,0 +1,400 @@
+_	 3156
+'	 991
+a	 829
+t	 788
+k	 788
+n	 752
+e	 640
+h	 602
+ë	 551
+s	 495
+w	 466
+ö	 422
+y	 403
+u	 397
+'_	 368
+_n	 330
+i	 269
+.	 269
+._	 240
+e'	 238
+ô	 219
+a'	 209
+ne	 209
+e_	 194
+_ne	 184
+wa	 172
+_k	 164
+kw	 162
+á	 154
+e'_	 146
+_t	 145
+'t	 141
+"	 141
+ë'	 134
+ê	 132
+_h	 131
+é	 129
+ak	 129
+ne_	 126
+ta	 123
+_ne_	 123
+at	 121
+u'	 121
+hu	 118
+_u	 108
+ka	 107
+í	 106
+nö	 105
+N	 103
+ö'	 100
+hs	 95
+ha	 95
+te	 94
+ya	 93
+_ë	 92
+kh	 90
+'k	 86
+ú	 85
+æ	 84
+ni	 84
+'.	 84
+wë	 83
+ny	 83
+sh	 80
+_N	 80
+'._	 76
+ö_	 76
+kë	 72
+_"	 71
+ën	 70
+th	 69
+yu	 66
+_w	 66
+ëh	 66
+t_	 66
+ô_	 66
+Ne	 65
+Ne'	 65
+'s	 64
+ne'	 64
+"_	 64
+_.	 63
+_._	 61
+Ne'_	 61
+,	 60
+ne'_	 58
+në	 58
+kwa	 57
+_ne'	 57
+öt	 57
+a't	 57
+ek	 56
+s_	 56
+ët	 55
+i'	 55
+_hu	 54
+T	 54
+ë_	 54
+_s	 54
+_Ne	 53
+të	 53
+tö	 53
+_Ne'	 53
+_ne'_	 53
+ht	 53
+-	 53
+ts	 52
+ya'	 52
+ë'_	 51
+_wa	 51
+_Ne'_	 51
+'ö	 50
+íy	 50
+_ka	 50
+as	 50
+ní	 49
+un	 49
+ê_	 49
+ty	 48
+hu_	 48
+ke	 48
+u_	 48
+,_	 47
+yô	 46
+he	 46
+ye	 46
+kê	 45
+si	 45
+nô	 44
+khu	 44
+a'k	 44
+_a	 43
+ák	 43
+wat	 42
+'ë	 42
+nö'	 42
+wá	 42
+aw	 41
+an	 41
+we	 41
+ôt	 41
+i_	 41
+_kh	 41
+tak	 41
+_te	 41
+ik	 41
+_khu	 40
+ës	 40
+yö	 40
+k_	 39
+khu_	 39
+yu'	 38
+hö	 38
+wën	 38
+n-	 38
+ëhs	 38
+_ha	 38
+wa'	 38
+_n-	 37
+sa	 37
+?	 37
+_T	 37
+æ'	 37
+_un	 36
+hô	 36
+wé	 36
+ah	 36
+_khu_	 35
+iy	 35
+ëk	 35
+ut	 35
+ök	 35
+öh	 35
+te'	 35
+u'_	 35
+_kë	 34
+yô_	 34
+ha'	 34
+st	 34
+ti	 34
+ta'	 34
+u't	 33
+ya't	 33
+'t_	 33
+'ö_	 33
+akw	 33
+ôk	 33
+níy	 32
+'ta	 32
+ku	 32
+ui	 32
+_sh	 32
+aa	 31
+én	 31
+ay	 31
+ënö	 31
+â	 30
+se	 30
+tw	 30
+yë	 30
+(_	 29
+_(_	 29
+_)_	 29
+us	 29
+_ëhs	 29
+(	 29
+kö	 29
+_ëh	 29
+ae	 29
+hë	 29
+_)	 29
+)_	 29
+_(	 29
+sy	 29
+)	 29
+ëë	 28
+ôn	 28
+sk	 28
+tá	 28
+té	 28
+tk	 28
+ên	 28
+kê_	 28
+a_	 28
+án	 27
+_huik	 27
+ön	 27
+_hui	 27
+kwé	 27
+huik	 27
+ék	 27
+hui	 27
+uik	 27
+_na	 27
+na	 27
+a'_	 26
+uikê	 26
+_ni	 26
+."	 26
+ææ	 26
+wi	 26
+huikê	 26
+ikê	 26
+nya	 25
+."_	 25
+?"	 25
+të'	 25
+íyu	 25
+awë	 25
+sn	 25
+në_	 24
+ö'_	 24
+ikê_	 24
+ekh	 24
+'ke	 24
+uikê_	 24
+?"_	 24
+tek	 24
+êt	 24
+',	 24
+"N	 23
+_ta	 23
+'a	 23
+hk	 23
+tê	 23
+tsi	 23
+wö	 23
+yu'_	 23
+_"N	 23
+íyu'	 23
+níyu	 23
+a'ta	 23
+é'	 23
+níyu'	 23
+shô	 22
+wëní	 22
+kwa'	 22
+ëní	 22
+kwë	 22
+_u'	 22
+ey	 22
+ëníyu	 22
+K	 22
+ai	 22
+_shô	 22
+úw	 22
+aö	 22
+ëht	 22
+ëníy	 22
+kwe	 22
+wëníy	 22
+_he	 22
+_te'	 21
+ún	 21
+s.	 21
+nöh	 21
+ëö	 21
+_ëk	 21
+'sh	 21
+kë'	 21
+htö	 21
+H	 21
+ata	 21
+U	 20
+'h	 20
+_ha'	 20
+ææ'	 20
+ae_	 20
+a'ke	 20
+ény	 20
+unö	 20
+we'	 20
+wë'	 20
+i'_	 20
+kës	 20
+ya'ta	 19
+es	 19
+awëní	 19
+hô_	 19
+uk	 19
+awën	 19
+hw	 19
+ë'.	 19
+ô'	 19
+tö'	 19
+sé	 19
+ë'ë	 19
+ë'._	 19
+'ëë	 19
+hkw	 19
+-a	 19
+twa	 19
+'kw	 18
+he_	 18
+_K	 18
+nöt	 18
+hsa	 18
+hsi	 18
+ôni	 18
+aya	 18
+is	 18
+ëë'	 18
+kæ	 18
+skw	 18
+uw	 18
+',_	 18
+e't	 18
+kææ	 18
+ka'	 18
+nae	 17
+shô_	 17
+sat	 17
+niy	 17
+ëts	 17
+ath	 17
+ye'	 17
+í_	 17
+'ëë'	 17
+'u	 17
+_ët	 17
+ës_	 17
+_kës	 17
+_y	 17
+kak	 17
+ö'ö	 17
+kat	 17
+_th	 17
+'ë_	 17
+út	 17
+u'k	 17
+_H	 17
+tekh	 17
+s._	 17
+wê	 17
+_nae	 17
+kwá	 17
+_shô_	 17
+yê	 17
+öte	 16
+sha	 16
+ke_	 16
+k.	 16
+si'	 16
+hö'	 16
+yá	 16
+hta	 16
+kn	 16
+_nae_	 16
+hse	 16
+ké	 16
+ë'ë_	 16
+unë	 16
+nya'	 16
+nae_	 16
+nê	 16
+á'	 16
+ás	 16
+tô	 16
+a's	 16
+a'u	 16
diff --git a/libtextcat/data/new_fingerprints/lm/nepali.lm b/libtextcat/data/new_fingerprints/lm/nepali.lm
new file mode 100644
index 000000000000..5d3507646f93
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/nepali.lm
@@ -0,0 +1,400 @@
+_	 7044
+f	 2698
+]	 1196
+g	 933
+s	 815
+l	 781
+/	 698
+;	 662
+k	 645
+d	 635
+]_	 630
+f_	 611
+sf	 549
+f]	 541
+n	 526
+t	 460
+o	 412
+j	 399
+f]_	 374
+L	 365
+_;	 364
+x	 356
+_k	 353
+{	 337
+b	 323
+u	 321
+'	 303
+df	 299
+sf]	 290
+_l	 283
+sf]_	 265
+g]	 245
+G	 232
+e	 231
+|	 227
+a	 222
+/_	 222
+L_	 211
+_g	 210
+c	 207
+df_	 207
+{_	 207
+_c	 201
+g_	 201
+kf	 184
+f/	 177
+_u	 171
+/f	 168
+P	 163
+_/	 162
+k|	 161
+_s	 161
+}	 159
++	 158
+h	 151
+fn	 150
+n]	 145
+of	 141
+tf	 140
+:	 136
+p	 136
+t_	 134
+.	 133
+_k|	 133
+._	 133
+_e	 131
+_d	 131
+_f	 129
+_._	 127
+_.	 127
+n]_	 123
+;f	 119
+lj	 118
+O	 118
+?	 118
+q	 118
+nf	 118
+y	 116
+_a	 113
+m	 111
+Ps	 110
+r	 110
+fg	 106
+w	 105
+sf_	 103
+lg	 102
+g]_	 100
+gf	 94
+_g]	 91
+Psf	 90
+x?	 89
+fd	 88
+fO	 88
+_lj	 85
+]s	 85
+z	 85
+s_	 84
+_p	 82
+_sf	 80
+D	 79
+kl	 78
+_;f	 78
+f/_	 77
+cf	 77
+}_	 76
+Psf]	 76
+jf	 76
+,	 75
+fl	 75
+\	 75
+_x	 74
+kfn	 74
+f{	 74
+_/f	 74
+]k	 73
+of]	 73
+,_	 72
+v	 72
+lt	 72
+_cf	 72
+_b	 71
+O{	 70
+i	 69
+xf	 68
+]kf	 68
+_/_	 68
+Psf]_	 68
+_h	 67
+g]kfn	 67
+g]k	 67
+d_	 67
+g]kf	 67
+O{_	 67
+]kfn	 67
+_g]k	 66
+g'	 66
+_g]kf	 66
+o_	 64
+"	 64
+;b	 63
+Gq	 63
+f+	 63
+n_	 63
+fk	 62
+sf/	 62
+/L	 62
+_kl	 62
+I	 61
+T	 61
+/s	 61
+If	 61
+dG	 60
+_j	 60
+]sf	 60
+;_	 59
+u_	 59
+yf	 59
+dGq	 58
+fO{	 58
+af	 57
+eP	 57
+fs	 57
+fO{_	 57
+fj	 56
+f;	 56
+qL	 56
+l/	 55
+\_	 55
+;D	 54
+dGqL	 54
+GqL	 54
+;+	 53
+g\	 53
+/sf	 52
+nfO	 51
+_kf	 51
+ug	 51
+pg	 51
+:t	 51
+fp	 50
+_ug	 50
+u/	 50
+lg_	 49
+ePs	 49
+fdf	 48
+cl	 48
+nfO{_	 48
+nfO{	 48
+;/	 48
+_cl	 47
+F	 47
+'/	 47
+g\_	 47
+_r	 47
+fo	 47
+_eP	 47
+]{	 46
+Z	 46
+/L_	 46
+_f_	 45
+ePsf	 45
+gd	 45
+_;D	 45
+if	 45
+Gb	 44
+lb	 44
+Q	 44
+_n	 44
+fsf	 44
+]sf]	 43
++;	 43
+nL	 43
+lx	 43
+_t	 43
+_:	 42
++;b	 42
+_o	 42
+fdf_	 42
+bf	 42
+hf	 42
+_lg	 42
+ePsf]	 41
+j_	 41
+ln	 41
+ef	 41
+/]	 41
+_df	 41
+To	 40
+klg_	 40
+_klg_	 40
+]sf]_	 40
+klg	 40
+_klg	 40
+_u/	 40
+f{_	 40
+_ePs	 40
+'g	 40
+Gg	 39
+:y	 39
+_g\	 39
+f}	 39
+kf_	 39
+:tf	 38
+]{_	 38
+fpg	 38
+b'	 38
+hg	 38
+g]{	 38
+jZ	 38
+_;+	 37
+gs	 37
+wf	 37
+o{	 37
+GqL_	 37
+l_	 37
+qL_	 37
+dGqL_	 37
+gf_	 37
+];	 37
+_ePsf	 36
+x'	 36
+?_	 36
+!	 36
+fx	 35
+u|	 34
+;d	 34
+_lb	 34
+fn_	 34
+_P	 34
+fg_	 34
+=	 34
+bn	 34
+Zj	 34
+o;	 34
+g]{_	 34
+_g\_	 34
+kIf	 33
+dl	 33
+kI	 33
+ljZj	 33
+jZj	 33
+rf	 33
++u	 33
+]d	 33
+ljZ	 33
+nL_	 32
+f+;	 32
+fnL	 32
+gL	 32
+;/sf	 32
+tf_	 32
+wfg	 32
+_;/	 32
+Qm	 32
+fb	 32
+f;_	 32
+ld	 32
+;/sf/	 32
+/sf/	 32
+_x'	 32
+;/s	 32
+;f+	 32
+_;f+	 32
+fu	 32
+x?_	 32
+;f+;	 31
+_k|:t	 31
+s'	 31
+_kI	 31
+_k|:	 31
+of]_	 31
+_kIf	 31
+_;f+;	 31
+]l	 31
+k|:	 31
+bg	 31
+_;/s	 31
+|:	 31
+f+;b	 31
+_;/sf	 31
+|:t	 31
+|]	 31
+k|:t	 31
+m_	 31
+;f+;b	 31
+Jo	 30
+k|wf	 30
+|w	 30
+|wf	 30
+k|w	 30
+km	 30
+J	 30
+k|wfg	 30
+|wfg	 30
+]t	 30
+@	 30
+;f]	 30
+b_	 29
+>	 29
+kfn_	 29
+fn]	 29
+gsf	 29
+sf+	 29
+Zjf	 29
+]kfn_	 29
+jif	 29
+ji	 29
+jf;	 29
+_k|w	 29
+fgd	 29
+_k|wf	 29
+Zjf;	 29
+ljZjf	 28
+jZjf;	 28
+]n	 28
+_z	 28
+_s'	 28
+_dG	 28
+|];	 28
+_;d	 28
+jZjf	 28
+u|]	 27
+gdGq	 27
+gdG	 27
+?n	 27
+x'g	 27
+|wfgd	 27
+wfgd	 27
+gdGqL	 27
++u|]	 27
+f+u	 27
+fgdG	 27
+u|];	 27
++u|];	 27
+wfgdG	 27
+dfg	 27
+a}	 27
+_dGq	 27
+f+u|	 27
+fgdGq	 27
+sf+u|	 27
+_sf+u	 27
+f+u|]	 27
++u|	 27
+sf+u	 27
+_sf+	 27
+x?n	 27
+S	 26
+_To	 26
+]kfnL	 26
+_!	 26
+_T	 26
+ul	 26
+/f]	 26
+fsf]	 26
+af_	 26
+;s	 26
+kfnL	 26
+|:tf	 26
+k|:tf	 26
diff --git a/libtextcat/data/new_fingerprints/lm/norwegian.lm b/libtextcat/data/new_fingerprints/lm/norwegian.lm
new file mode 100644
index 000000000000..f2c3cec3aae3
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/norwegian.lm
@@ -0,0 +1,400 @@
+_	 22970
+e	 6833
+n	 4206
+r	 3516
+t	 3112
+a	 2587
+s	 2440
+i	 2112
+l	 1901
+o	 1900
+n_	 1875
+r_	 1761
+k	 1713
+g	 1630
+en	 1615
+m	 1508
+e_	 1450
+d	 1444
+er	 1436
+h	 1306
+t_	 1300
+_h	 1180
+_s	 1148
+er_	 1105
+v	 982
+en_	 976
+an	 919
+.	 901
+._	 791
+_.	 781
+et	 770
+g_	 762
+_._	 726
+å	 725
+u	 719
+f	 709
+p	 702
+ha	 682
+_ha	 672
+de	 657
+te	 651
+_e	 621
+et_	 614
+re	 581
+ne	 565
+_o	 554
+an_	 544
+ke	 534
+_,	 522
+,_	 522
+,	 522
+_,_	 522
+_f	 519
+_m	 515
+or	 503
+_d	 483
+_i	 480
+å_	 479
+se	 476
+m_	 469
+nn	 454
+b	 449
+me	 441
+ø	 434
+_a	 413
+st	 404
+_t	 398
+og	 380
+_v	 377
+_og	 366
+ar	 364
+el	 364
+le	 361
+i_	 356
+om	 353
+og_	 351
+_og_	 351
+li	 350
+_k	 346
+_de	 339
+ge	 339
+han	 337
+y	 333
+_han	 332
+ve	 330
+kk	 323
+in	 311
+_b	 307
+fo	 301
+j	 301
+il	 298
+_H	 291
+H	 291
+han_	 288
+_han_	 288
+for	 287
+ik	 281
+l_	 278
+kke	 277
+tt	 276
+ti	 270
+ne_	 270
+d_	 269
+ed	 269
+om_	 268
+nne	 266
+_me	 264
+ng	 257
+_er	 257
+_fo	 256
+eg	 256
+_se	 256
+_g	 256
+un	 255
+ig	 255
+sk	 253
+_er_	 252
+_p	 252
+_for	 250
+ke_	 249
+_n	 238
+_l	 233
+al	 232
+ør	 222
+s_	 221
+ar_	 215
+at	 214
+_en	 211
+he	 211
+pe	 209
+_i_	 208
+am	 200
+es	 200
+si	 200
+enn	 197
+det	 195
+or_	 193
+vi	 190
+ns	 189
+ikk	 188
+det_	 185
+so	 185
+un_	 183
+il_	 181
+nd	 181
+te_	 181
+"_	 180
+"	 180
+_"_	 180
+_"	 180
+em	 179
+_ti	 176
+kke_	 176
+lig	 174
+ten	 174
+Ha	 173
+_Ha	 173
+re_	 172
+ikke	 168
+je	 165
+Han	 165
+ter	 165
+_Han	 165
+eg_	 164
+på	 164
+_på	 163
+_si	 163
+_å	 163
+_Han_	 162
+Han_	 162
+på_	 162
+_på_	 161
+til	 160
+som	 160
+_so	 159
+den	 159
+_det	 157
+ed_	 155
+ll	 155
+_ik	 155
+rt	 155
+som_	 153
+ra	 152
+a_	 152
+har	 152
+nt	 152
+de_	 152
+tr	 151
+v_	 151
+_har	 151
+ka	 151
+ig_	 150
+_som	 150
+for_	 150
+_som_	 150
+_en_	 149
+hu	 149
+_ikk	 148
+_ham	 148
+ham	 148
+ste	 148
+_det_	 148
+_ikke	 148
+enne	 148
+ikke_	 148
+har_	 147
+nge	 147
+D	 147
+_har_	 147
+_D	 147
+am_	 147
+ere	 147
+ham_	 146
+_ham_	 146
+it	 145
+_he	 144
+_til	 144
+av	 143
+va	 140
+men	 140
+år	 140
+_ve	 140
+_hu	 139
+ta	 139
+pen	 137
+sp	 137
+_st	 135
+tte	 135
+la	 135
+_E	 133
+E	 133
+den_	 130
+is	 130
+til_	 128
+_r	 128
+tt_	 128
+år_	 127
+k_	 124
+_å_	 124
+ri	 124
+_til_	 124
+at_	 123
+ene	 123
+seg	 123
+_av	 123
+med	 122
+_vi	 122
+_seg	 122
+seg_	 121
+_seg_	 121
+_for_	 120
+nne_	 120
+ut	 120
+_u	 119
+mm	 119
+mme	 119
+De	 118
+_De	 118
+_at	 118
+_hun	 117
+hun	 117
+ko	 117
+be	 116
+_at_	 115
+ter_	 115
+pen_	 114
+ker	 113
+hun_	 113
+_hun_	 113
+on	 111
+lig_	 111
+..	 110
+hen	 107
+_med	 107
+rs	 106
+ser	 106
+med_	 105
+_men	 104
+_hen	 104
+_sk	 104
+_med_	 104
+ak	 103
+ans	 103
+ker_	 102
+av_	 101
+_ka	 101
+no	 100
+ver	 100
+ler	 99
+J	 99
+spe	 99
+ten_	 99
+_J	 99
+ene_	 98
+ld	 98
+hv	 98
+_av_	 98
+ger	 97
+ni	 96
+gen	 96
+ie	 95
+ser_	 94
+_et	 94
+spen	 94
+_hv	 94
+men_	 93
+Espe	 92
+Es	 92
+_Esp	 92
+_Es	 92
+_Espe	 92
+Esp	 92
+_al	 92
+Espen	 92
+lle	 89
+rem	 89
+id	 89
+fø	 89
+ei	 88
+inn	 88
+rd	 88
+enne_	 88
+_henn	 87
+henne	 87
+henn	 87
+kt	 86
+spen_	 86
+_om	 86
+ler_	 86
+da	 86
+ett	 86
+itt	 86
+bl	 85
+to	 85
+_Je	 84
+ger_	 84
+Je	 84
+æ	 84
+ma	 83
+ing	 83
+ær	 83
+ns_	 83
+eli	 82
+ang	 82
+_be	 82
+så	 82
+_den	 82
+pp	 81
+rk	 81
+dr	 81
+oe	 81
+ss	 81
+_fø	 80
+ek	 80
+le_	 79
+_no	 79
+kj	 78
+elig	 78
+nes	 78
+nn_	 77
+nk	 77
+fr	 77
+sl	 77
+my	 77
+kan	 77
+så_	 76
+as	 76
+_om_	 76
+_kan	 75
+_ko	 75
+_bl	 73
+Hu	 73
+nen	 73
+_Hu	 73
+eng	 73
+gj	 73
+rt_	 72
+ge_	 72
+ba	 72
+lv	 71
+rer	 71
+nde	 71
+ls	 70
+lo	 70
+ga	 70
+_noe	 70
+ro	 70
+_den_	 70
+_ut	 70
+noe	 70
+Hun	 69
+Hun_	 69
+_in	 69
+_Hun	 69
+_Hun_	 69
+ren	 68
+øre	 68
+ør_	 68
+sen	 68
+sa	 67
diff --git a/libtextcat/data/new_fingerprints/lm/persian.lm b/libtextcat/data/new_fingerprints/lm/persian.lm
new file mode 100644
index 000000000000..858f468ae54a
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/persian.lm
@@ -0,0 +1,400 @@
+_	 12318
+?	 5938
+¤	 2613
+?_	 1815
+¢	 1745
+þ	 1569
+ø	 1546
+õ	 1422
+-	 1333
+÷	 1155
+ù	 991
+¨	 841
+_ù	 778
+ö	 761
+î	 693
+ü	 664
+_ö	 663
+ª	 660
+¤?	 631
+õ_	 624
+_?	 601
+?¤	 598
+¥	 589
+_¤	 565
+??	 564
+ý	 513
+¢_	 486
+_ü	 473
+_ý	 469
+þ?	 459
+û	 428
+ø_	 427
+_¢	 398
+î_	 392
+ó	 390
+ê	 384
+ö?	 379
+÷?	 361
+_ø	 337
+_-	 334
+>	 327
+ú	 324
+_ö?	 319
+ù?	 313
+_ø_	 308
+ð	 305
+¤¢	 303
+¤_	 297
+?õ	 290
+¨?	 285
+¢÷	 272
+-_	 271
+S	 266
+_ù?	 265
+ô	 259
+-¨	 255
+¡	 255
+??_	 255
+ý?	 254
+¥?	 250
+Y	 246
+¤¢_	 245
+ì	 243
+_ý?	 238
+?¢	 234
+_¥	 229
+ò	 229
+_S	 228
+¤ø	 216
+ø¤	 215
+?þ	 215
+?¨	 214
+_¤¢	 214
+ñ	 208
+þ?_	 207
+¢¤	 203
+?-	 202
+_ô	 199
+ù?_	 199
+öþ	 195
+¨_	 190
+¨?_	 190
+_??	 189
+õ?	 188
+.	 188
+_¤¢_	 185
+_ñ	 183
+?ø	 181
+_öþ	 180
+¢?	 177
+*	 176
+÷_	 176
+_ù?_	 174
+?û	 173
+¤þ	 172
+ª_	 170
+þõ	 164
+ä	 161
+¯	 158
+-¨?	 156
+û_	 155
+¤?_	 155
+_¥?	 152
+üõ	 151
+ý¤	 150
+_¤?	 146
+¥?_	 144
+þ¤	 143
+¢ø	 141
+?¤_	 140
+*_	 138
+ü÷	 137
+?÷	 136
+¬	 133
+ùî	 132
+_ý¤	 131
+-ª	 131
+ø?	 130
+?ú	 129
+_.	 129
+þó	 129
+¡_	 128
+ù¢	 124
+¤õ	 121
+¤-	 120
+ùî_	 120
+_ùî	 120
+_??_	 119
+ª?	 119
+-¨?_	 119
+ã	 118
+-?	 118
+>_	 116
+öþ?	 114
+ê_	 111
+¢þ	 109
+_¥?_	 109
+_ü÷	 109
+_ùî_	 108
+_öþ?	 107
+ö?¤	 107
+©	 106
+_¢÷	 106
+.¢	 104
+?¥	 103
+_?¤	 103
+¤ê	 103
+ó?	 103
+þ¢	 103
+ñ?	 102
+ªî	 100
+?î	 100
+?¤?	 98
+ð_	 98
+ý?û	 96
+¤ú	 95
+öþ?_	 95
+_©	 94
+§	 94
+Y_	 94
+_ö?¤	 93
+_ý?û	 93
+¥ø	 92
+øª	 91
+_ñ?	 91
+_öþ?_	 91
+?¨_	 90
+÷?_	 90
+óþ	 90
+õ?_	 90
+ü-	 90
+øõ	 89
+:	 89
+ªî_	 88
+ü÷?	 88
+öø	 88
+_ù¢	 87
+-ê	 86
+þ÷	 85
+_öø	 83
+,	 82
+þõ_	 82
+þ¨	 82
+?¢_	 80
+®	 80
+?¤þ	 79
+_ü÷?	 79
+¢ª	 77
+???	 77
+øþ	 76
+_-?	 75
+÷î	 75
+?ª	 75
+?ì	 75
+¤î	 74
+_¤ø	 73
+ä_	 73
+þóþ	 73
+û?	 73
+óþõ	 72
+þóþõ	 71
+ù¤	 71
+?>	 71
+ê?	 70
+_?¤_	 70
+_.¢	 70
+ø¡	 69
+à	 69
+_§	 68
+¥ø¤	 68
+þóþõ_	 67
+_ü-	 67
+¤øª	 67
+óþõ_	 67
+õû	 67
+¤ê_	 67
+¨õ	 67
+¤õ_	 66
+?-_	 65
+ù÷	 65
+ý?¤	 65
+öøþ	 64
+¤þ?	 64
+¬_	 64
+?ð	 63
+?-¨	 63
+ø-	 63
+_ý?¤	 62
+ø?_	 62
+ø¤_	 62
+_-¨	 61
+õþ	 61
+øþóþõ	 60
+øþóþ	 60
+øþó	 60
+?ù	 60
+øªî	 60
+_¢ø	 60
+¤øªî	 60
+_öøþ	 60
+-ª?	 60
+ì_	 60
+¨¤	 60
+ý¤?	 60
+÷þ	 59
+öøþóþ	 59
+¯?	 59
+_¢?	 59
+öøþó	 59
+¢ª_	 59
+¤??	 58
+¤?¥	 58
+_üõ	 58
+.-	 58
+?¡	 58
+ø÷	 57
+í	 57
+¢¤î	 57
+?¤?_	 57
+þ?¤	 57
+ù-	 57
+üõ_	 56
+ñ?¨	 56
+øõ_	 56
+?¤þ?	 56
+ú?	 56
+î¤	 56
+¤?¢	 56
+õû_	 55
+ô?	 55
+ª?¢	 55
+_öøþó	 55
+-ª?¢	 55
+þ_	 55
+ö?¤þ	 55
+¤î_	 55
+S¤	 55
+üþ	 54
+_S¤	 53
+øªî_	 53
+_ù¤	 53
+ò¢	 53
+¤ò	 53
+¤øªî_	 53
+ø¡_	 52
+¢÷?	 52
+û¤	 52
+üþ?	 52
+õ>	 52
+-õ	 52
+¢¤?	 52
+üð	 52
+ì?	 52
+_í	 52
+î?	 52
+üó	 52
+??¤	 52
+ð÷	 51
+¤ò¢	 51
+-þ	 51
+_ý¤?	 51
+¡?	 50
+_¢¤	 50
+¢¤î_	 50
+.-¨	 50
+ö?õ	 50
+ë	 50
+_ô?	 50
+ø¢	 50
+_ñ?¨	 49
+.¢÷	 49
+÷¤	 49
+ý?¤?	 49
+ú-	 48
+_üð	 48
+_ö?¤þ	 48
+¤þ?_	 48
+ò¢_	 48
+ûù	 48
+ú?_	 48
+¤ò¢_	 47
+ê¤	 47
+â	 47
+.-¨?	 47
+_¢þ	 47
+>÷	 47
+úª	 47
+÷?õ	 47
+£	 47
+?¤þ?_	 47
+?ûù	 47
+¤¯	 46
+_.-	 46
+_ý?¤?	 46
+õ¤	 46
+õó	 46
+-¤	 46
+_üþ	 46
+¥þ	 46
+¤ð	 45
+ôþ	 45
+_üó	 45
+ö?-	 45
+§þ	 45
+_ë	 45
+f	 45
+õ-	 44
+_ù-	 44
+úõ	 44
+_üþ?	 44
+ü-ª	 44
+-î	 44
+ð¢	 44
+ö?¤þ?	 44
+õª	 44
+.-¨?_	 44
+¨õ_	 44
+¤ª	 44
+_-¨?	 44
+¤?î	 43
+ä?	 43
+é	 43
+?õ_	 43
+_¤øªî	 43
+þª	 43
+?ê	 43
+?î_	 43
+_¤øª	 43
+¯_	 43
+¤¨	 43
+þ??	 42
+Y?	 42
+¥_	 42
+÷÷	 42
+÷õ	 42
+_¥ø	 42
+þ¨?	 42
+¢õ	 42
+/	 42
+_â	 42
+???_	 42
+_¥ø¤	 42
+_ù÷	 42
+s	 42
+¢÷÷	 42
+ö?-¨	 41
+÷ø	 41
+ù÷?	 41
+?*	 41
+S¤ò¢	 41
+_ö?õ	 41
+ñþ	 41
+_.-¨	 41
+îþ	 41
+÷¢	 41
+ùõ	 41
+S¤ò	 41
+ªø	 41
+ý?¤?_	 40
+¤úª	 40
diff --git a/libtextcat/data/new_fingerprints/lm/polish.lm b/libtextcat/data/new_fingerprints/lm/polish.lm
new file mode 100644
index 000000000000..eac3b27eca6a
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/polish.lm
@@ -0,0 +1,400 @@
+_	 31480
+a	 7945
+i	 7766
+e	 7462
+o	 6838
+z	 5104
+n	 5077
+r	 4178
+w	 4139
+s	 3596
+c	 3580
+y	 3569
+t	 3381
+d	 3027
+k	 2819
+p	 2639
+m	 2494
+ie	 2484
+u	 2016
+l	 1947
+j	 1932
+ni	 1930
+e_	 1746
+_p	 1712
+³	 1649
+a_	 1496
+o_	 1431
+,	 1368
+,_	 1366
+b	 1296
+_w	 1257
+g	 1249
+i_	 1140
+.	 1118
+_s	 1045
+ze	 1041
+._	 1035
+_n	 997
+nie	 958
+cz	 956
+rz	 952
+h	 950
+_z	 933
+ê	 918
+ow	 911
+ie_	 902
+y_	 899
+na	 885
+ch	 871
+po	 864
+pr	 863
+wi	 851
+st	 847
+¿	 835
+±	 832
+an	 814
+ó	 800
+ra	 778
+zy	 766
+ia	 726
+za	 718
+_t	 699
+wa	 692
+ro	 692
+_d	 683
+_pr	 675
+¶	 661
+w_	 658
+sz	 652
+_po	 649
+_o	 628
+m_	 613
+li	 613
+dz	 611
+ki	 611
+en	 609
+mi	 593
+ta	 571
+ci	 564
+ej	 562
+nie_	 558
+_m	 553
+_k	 549
+ar	 543
+go	 541
+_i	 540
+em	 532
+od	 525
+yc	 520
+a³	 511
+rze	 508
+do	 504
+eg	 503
+ko	 502
+ac	 482
+to	 478
+_na	 467
+_ni	 467
+h_	 466
+ch_	 466
+æ	 465
+iê	 461
+_b	 458
+on	 458
+u_	 458
+zi	 454
+ka	 450
+er	 448
+sk	 447
+si	 447
+wy	 444
+te	 437
+ak	 434
+ê_	 431
+_j	 429
+je	 429
+z_	 427
+ny	 422
+aw	 422
+ne	 420
+ów	 418
+_w_	 415
+_c	 414
+ego	 412
+prz	 412
+_r	 410
+al	 407
+³a	 405
+"	 405
+re	 405
+es	 401
+_nie	 396
+dzi	 394
+ty	 389
+j_	 380
+ic	 380
+_prz	 379
+ad	 367
+ej_	 364
+le	 359
+æ_	 358
+ed	 354
+ych	 346
+_za	 346
+_do	 344
+zn	 344
+go_	 344
+ani	 343
+_i_	 342
+no	 339
+or	 337
+³o	 336
+tr	 334
+P	 330
+os	 329
+am	 329
+da	 328
+ec	 327
+ol	 325
+±_	 325
+by	 322
+ego_	 321
+at	 321
+¿e	 319
+ym	 317
+wie	 314
+³_	 312
+-	 310
+na_	 309
+_si	 303
+W	 301
+as	 301
+wo	 300
+pa	 299
+siê	 295
+nia	 293
+owa	 292
+o¶	 286
+_P	 283
+el	 282
+_siê	 279
+ja	 278
+rzy	 276
+prze	 276
+_wy	 275
+iê_	 269
+in	 267
+_-	 267
+de	 267
+kie	 267
+dn	 264
+ob	 262
+_u	 261
+ych_	 260
+-_	 258
+ez	 257
+_-_	 256
+¶c	 255
+ws	 255
+¶ci	 254
+em_	 253
+_siê_	 253
+siê_	 253
+_nie_	 253
+kt	 252
+ski	 252
+we	 251
+_g	 251
+_W	 250
+t_	 249
+_prze	 249
+_je	 248
+aj	 247
+_a	 247
+¿e_	 246
+_¿	 244
+ia_	 243
+eni	 241
+om	 240
+la	 240
+k_	 235
+mo	 235
+f	 234
+pi	 232
+is	 231
+cze	 231
+_z_	 230
+ñ	 228
+nt	 227
+ce	 224
+sta	 221
+ry	 220
+ma	 219
+cj	 219
+zie	 218
+ek	 216
+oc	 213
+dy	 212
+owi	 208
+sp	 208
+K	 208
+tó	 205
+_"	 204
+ud	 203
+S	 202
+ier	 202
+pra	 202
+czn	 201
+ys	 200
+nia_	 199
+j±	 198
+_¿e	 196
+oz	 194
+N	 192
+zo	 191
+dzie	 190
+ku	 190
+ów_	 189
+czy	 189
+_mi	 188
+_¿e_	 187
+mie	 186
+do_	 186
+iej	 185
+ym_	 185
+_do_	 184
+cy	 184
+_pa	 183
+y³	 182
+_na_	 181
+zy_	 181
+ew	 180
+_l	 180
+_cz	 178
+_by	 178
+ru	 177
+to_	 175
+±c	 175
+_wi	 175
+ln	 174
+_K	 171
+ok	 170
+ot	 170
+raw	 169
+nych	 168
+nyc	 168
+az	 168
+ik	 167
+bi	 167
+i,_	 166
+i,	 166
+_te	 165
+tu	 163
+wan	 163
+et	 162
+J	 162
+ór	 161
+cie	 160
+_od	 160
+ba	 160
+oj	 159
+o¶c	 158
+i³	 158
+_ro	 158
+og	 158
+mu	 158
+A	 158
+o¶ci	 158
+d_	 157
+tw	 156
+io	 155
+gr	 155
+_J	 155
+_N	 155
+_to	 155
+us	 155
+¿_	 154
+aæ	 154
+ach	 154
+yd	 153
+_kt	 153
+_ko	 152
+_st	 152
+pow	 151
+yt	 150
+kr	 149
+_S	 149
+a³_	 149
+ak_	 149
+li_	 148
+T	 148
+ur	 148
+sa	 148
+op	 147
+yw	 147
+ent	 147
+bo	 146
+_sp	 145
+O	 145
+a,_	 144
+a,	 144
+iem	 144
+któ	 143
+praw	 143
+wn	 142
+tór	 142
+i±	 141
+³y	 141
+zu	 141
+dni	 140
+im	 139
+icz	 139
+ró	 139
+³e	 138
+któr	 137
+my	 137
+est	 136
+awi	 135
+przy	 134
+nych_	 134
+e,_	 132
+e,	 132
+ki_	 132
+pro	 131
+_któ	 131
+_któr	 131
+_przy	 130
+_ja	 129
+szy	 127
+ia³	 127
+Po	 127
+ania	 127
+M	 126
+ze_	 125
+ne_	 125
+ñs	 124
+_ty	 124
+sze	 124
+a¿	 124
+nn	 124
+pod	 124
+aæ_	 122
+B	 122
+za_	 122
+cza	 122
+³o_	 122
+Z	 122
+_to_	 121
+iu	 120
+zc	 119
+esz	 119
+skie	 118
+i.	 118
+_ka	 117
+so	 117
+trz	 117
+o¿	 116
+ieg	 116
+nik	 116
+ga	 116
diff --git a/libtextcat/data/new_fingerprints/lm/portuguese.lm b/libtextcat/data/new_fingerprints/lm/portuguese.lm
new file mode 100644
index 000000000000..4e1a5d7698e4
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/portuguese.lm
@@ -0,0 +1,400 @@
+_	 35328
+a	 10423
+e	 10132
+o	 8919
+s	 6795
+r	 6033
+i	 5443
+n	 4588
+d	 4531
+t	 4217
+m	 3476
+u	 3404
+o_	 3240
+a_	 3029
+e_	 2879
+c	 2756
+s_	 2461
+_d	 2379
+l	 2307
+p	 2242
+_a	 1753
+de	 1751
+,	 1660
+,_	 1658
+_e	 1454
+es	 1447
+os	 1412
+ra	 1343
+_p	 1328
+nt	 1302
+_de	 1248
+do	 1215
+en	 1176
+re	 1150
+as	 1123
+v	 1115
+m_	 1113
+de_	 1096
+er	 1082
+g	 1053
+_c	 1047
+da	 1008
+co	 986
+os_	 975
+te	 974
+ar	 950
+or	 943
+q	 938
+qu	 938
+_s	 908
+ta	 902
+_de_	 901
+_o	 858
+se	 841
+ue	 831
+to	 799
+ad	 777
+.	 761
+que	 752
+em	 751
+an	 748
+f	 746
+r_	 745
+b	 732
+st	 718
+is	 716
+al	 712
+_qu	 706
+_q	 706
+in	 701
+as_	 696
+ã	 695
+do_	 685
+ent	 678
+ão	 677
+_n	 671
+_co	 660
+_a_	 654
+_m	 646
+on	 645
+ç	 624
+ri	 623
+_que	 619
+ma	 602
+po	 581
+ia	 580
+ão_	 575
+._	 573
+na	 572
+me	 564
+ro	 554
+_t	 544
+pa	 533
+da_	 528
+h	 523
+ue_	 515
+ca	 511
+que_	 509
+nte	 503
+no	 499
+tr	 498
+am	 496
+em_	 491
+_que_	 487
+_se	 485
+om	 471
+io	 460
+_do	 459
+ti	 448
+ci	 445
+_da	 444
+nd	 442
+ei	 435
+ra_	 435
+pr	 427
+_r	 423
+_e_	 420
+_f	 420
+ss	 412
+es_	 412
+el	 407
+id	 406
+_o_	 399
+_pa	 390
+um	 379
+pe	 378
+_po	 376
+la	 374
+ir	 371
+á	 371
+ic	 362
+di	 362
+li	 359
+é	 359
+_re	 353
+ve	 353
+mo	 350
+s,	 349
+s,_	 349
+ou	 347
+com	 340
+sa	 338
+si	 338
+men	 337
+rt	 331
+_i	 330
+con	 330
+o,	 327
+_da_	 326
+o,_	 326
+se_	 325
+_com	 325
+ado	 323
+to_	 322
+ai	 322
+it	 320
+A	 319
+ec	 316
+dos	 316
+_em	 312
+ção	 310
+aç	 310
+çã	 310
+ara	 305
+so	 299
+tu	 299
+res	 297
+im	 296
+_pr	 295
+mi	 293
+ua	 292
+nto	 291
+ment	 290
+í	 290
+par	 288
+_do_	 287
+ce	 286
+est	 286
+u_	 284
+ente	 284
+S	 278
+l_	 278
+_u	 278
+"	 276
+ni	 276
+z	 274
+sta	 273
+nc	 272
+_em_	 270
+P	 269
+ção_	 267
+_v	 267
+at	 267
+dos_	 266
+_es	 262
+«	 259
+_«	 259
+te_	 258
+»	 257
+va	 255
+le	 252
+ur	 252
+_um	 252
+vi	 251
+_par	 250
+a,	 247
+a,_	 247
+_con	 247
+ant	 242
+lo	 240
+ia_	 240
+gu	 237
+ar_	 235
+ac	 235
+e,_	 234
+e,	 234
+no_	 232
+eg	 232
+il	 232
+ns	 232
+er_	 231
+_ma	 230
+por	 230
+_in	 228
+_l	 226
+ó	 225
+ont	 224
+_no	 223
+_P	 222
+tra	 220
+E	 219
+ida	 218
+is_	 217
+ol	 216
+açã	 215
+ter	 215
+ação	 215
+_A	 211
+un	 211
+-	 210
+_te	 210
+or_	 209
+ma_	 208
+_pe	 208
+ara_	 208
+C	 206
+ist	 202
+para	 202
+nta	 201
+ais	 201
+ut	 198
+nte_	 198
+j	 197
+dad	 196
+_na	 195
+am_	 195
+ade	 193
+ica	 191
+x	 190
+al_	 189
+O	 188
+des	 187
+_para	 187
+ada	 187
+nh	 186
+_se_	 186
+mp	 185
+ndo	 184
+R	 183
+_por	 181
+ação_	 181
+para_	 179
+eir	 177
+ui	 177
+vo	 177
+ou_	 177
+ta_	 177
+M	 176
+ria	 175
+tos	 175
+rr	 174
+D	 174
+io_	 174
+br	 174
+_di	 173
+õ	 173
+õe	 173
+fo	 173
+I	 172
+ões	 172
+_C	 171
+mo_	 171
+ov	 170
+pro	 169
+_os_	 169
+_os	 169
+das	 167
+iv	 166
+uma	 165
+gr	 165
+su	 164
+fi	 164
+um_	 162
+na_	 162
+ga	 162
+ais_	 161
+_S	 161
+lh	 159
+ort	 159
+cia	 158
+..	 157
+_est	 156
+cont	 156
+ig	 155
+á_	 154
+ran	 154
+ça	 154
+om_	 153
+_en	 152
+dade	 152
+_as	 152
+ho	 152
+ntr	 151
+nto_	 151
+fe	 150
+N	 149
+das_	 149
+uma_	 149
+ess	 149
+é_	 148
+ndo_	 147
+ob	 147
+»_	 147
+ul	 146
+ente_	 146
+go	 146
+ento	 144
+ver	 144
+_des	 144
+gi	 144
+ha	 142
+cu	 142
+idad	 142
+av	 141
+ões_	 141
+_pro	 141
+ura	 141
+ap	 139
+_com_	 139
+_ca	 139
+com_	 139
+ao	 139
+ne	 138
+od	 138
+_"	 137
+_M	 137
+pre	 137
+ras	 136
+_me	 136
+_ao	 136
+_no_	 134
+oc	 134
+str	 133
+tes	 133
+_b	 133
+and	 133
+_g	 133
+ro_	 133
+omo	 133
+_dos	 132
+_fo	 132
+_dos_	 132
+rn	 132
+mento	 131
+ito	 131
+ev	 131
+rio	 130
+ass	 130
+eu	 130
+be	 128
+os,	 128
+os,_	 128
+sp	 127
+_uma	 127
+ep	 126
+tad	 125
+s.	 125
+_uma_	 125
+_E	 125
+idade	 124
+_um_	 124
+nã	 124
+não	 124
+ct	 123
+ram	 123
+ado_	 123
+ela	 123
+omo_	 121
+iz	 121
+_an	 121
diff --git a/libtextcat/data/new_fingerprints/lm/quechua.lm b/libtextcat/data/new_fingerprints/lm/quechua.lm
new file mode 100644
index 000000000000..e59992d781b3
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/quechua.lm
@@ -0,0 +1,400 @@
+_	 5766
+a	 4900
+n	 1941
+i	 1666
+u	 1384
+s	 1032
+t	 995
+y	 939
+h	 929
+k	 915
+q	 909
+p	 882
+a_	 847
+an	 821
+r	 783
+m	 740
+c	 705
+l	 695
+ta	 637
+ch	 613
+ay	 587
+qa	 557
+pa	 490
+ha	 486
+e	 474
+ma	 457
+o	 441
+na	 434
+ku	 411
+j	 409
+un	 367
+w	 358
+in	 353
+,	 345
+,_	 344
+cha	 318
+ar	 317
+n_	 315
+as	 291
+wa	 289
+ta_	 269
+ll	 259
+man	 255
+_k	 248
+._	 243
+.	 243
+nt	 227
+am	 224
+pi	 222
+la	 222
+ka	 217
+ac	 214
+ni	 214
+at	 213
+aq	 213
+i_	 208
+ri	 207
+qa_	 204
+una	 204
+y_	 192
+aj	 192
+_p	 192
+is	 188
+_m	 181
+lla	 175
+ach	 174
+rq	 173
+us	 172
+an_	 171
+_ka	 171
+ata	 169
+rqa	 165
+sq	 163
+hu	 162
+sp	 161
+_w	 157
+nk	 157
+hay	 157
+_s	 156
+sqa	 155
+ki	 153
+kun	 152
+_c	 152
+al	 150
+nta	 149
+ap	 147
+ant	 146
+yk	 146
+ay_	 144
+spa	 141
+hi	 137
+_ch	 136
+_n	 136
+ya	 135
+'	 134
+j_	 133
+uy	 132
+ra	 132
+a,_	 132
+a,	 132
+ti	 130
+_a	 125
+nc	 125
+kuna	 122
+s_	 121
+su	 121
+ak	 121
+_ma	 118
+ana	 118
+ari	 115
+_t	 114
+ama	 114
+chi	 114
+ñ	 113
+a._	 111
+a.	 111
+nch	 111
+iy	 111
+all	 110
+aw	 110
+_r	 110
+anta	 109
+ayk	 109
+na_	 109
+chay	 108
+sa	 104
+_wa	 104
+si	 103
+chu	 102
+pa_	 101
+acha	 101
+_cha	 101
+pi_	 101
+qan	 100
+_pa	 99
+_q	 97
+aj_	 97
+awa	 97
+ank	 95
+nku	 95
+im	 94
+q_	 92
+uk	 92
+C	 92
+mu	 90
+tu	 89
+J	 89
+_ni	 88
+taj	 87
+_J	 87
+nin	 86
+_chay	 86
+u_	 86
+_C	 84
+wan	 83
+nta_	 81
+_j	 81
+mant	 80
+ut	 79
+in_	 79
+ik	 79
+manta	 79
+asq	 79
+yt	 78
+n,	 78
+asqa	 78
+n,_	 78
+pay	 78
+li	 77
+yn	 77
+nq	 76
+yta	 76
+ic	 76
+up	 76
+_Ch	 75
+yku	 75
+Ch	 75
+he	 75
+hay_	 74
+nan	 74
+ina	 74
+ur	 73
+er	 72
+S	 72
+arq	 72
+or	 72
+_l	 71
+_u	 71
+aq_	 70
+os	 70
+yp	 70
+anc	 69
+man_	 69
+mi	 69
+ich	 68
+_i	 68
+st	 67
+_S	 67
+arqa	 66
+it	 66
+anch	 66
+ru	 66
+aku	 65
+pu	 65
+ña	 65
+alla	 64
+mp	 64
+sqa_	 64
+'a	 64
+ayku	 63
+es	 63
+A	 63
+ia	 63
+_man	 63
+_Cha	 61
+Cha	 61
+taj_	 60
+api	 60
+_ll	 60
+wi	 60
+ayp	 60
+aman	 59
+g	 58
+anku	 58
+yki	 57
+ima	 57
+yni	 57
+oj	 57
+mana	 57
+anta_	 57
+_su	 57
+uc	 56
+isp	 56
+ispa	 56
+uch	 56
+M	 56
+ir	 56
+_h	 55
+nqa	 55
+kuy	 55
+ayt	 54
+_M	 54
+b	 54
+_y	 53
+_mana	 53
+:	 53
+uku	 53
+:_	 53
+nm	 53
+au	 52
+ayta	 52
+io	 52
+qo	 51
+an,_	 51
+apa	 51
+spa_	 51
+erq	 51
+_wi	 51
+erqa	 51
+_sa	 51
+an,	 51
+el	 50
+um	 50
+ana_	 50
+han	 50
+il	 50
+on	 49
+chay_	 49
+sta	 49
+_D	 49
+D	 49
+iku	 49
+aqa	 49
+che	 48
+en	 48
+yta_	 48
+Ma	 47
+P	 47
+_lla	 47
+_Je	 47
+yq	 47
+Je	 47
+ita	 47
+rqan	 47
+ypi	 46
+har	 46
+Jes	 46
+_Jes	 46
+ios	 46
+ayq	 46
+Dio	 46
+un_	 46
+kus	 46
+_Dio	 46
+taq	 46
+_Dios	 46
+_Ma	 46
+_Di	 46
+Dios	 46
+Di	 46
+d	 46
+kan	 45
+Chay	 45
+oq	 45
+_Chay	 45
+_pay	 45
+upa	 45
+mun	 45
+ata_	 44
+_tu	 44
+nis	 44
+re	 44
+paq	 44
+yo	 44
+ej	 44
+qay	 43
+ncha	 43
+ha_	 43
+_A	 43
+I	 43
+_kan	 43
+_nis	 43
+_P	 43
+nman	 43
+nma	 43
+ataj	 42
+ara	 42
+ku_	 42
+nata	 42
+nat	 42
+i,	 41
+tin	 41
+qh	 41
+t'	 41
+orq	 41
+nki	 41
+_ru	 41
+_ku	 41
+i,_	 41
+ip	 40
+ham	 40
+usq	 40
+_ya	 40
+qank	 39
+orqa	 39
+ayn	 39
+mana_	 39
+ray	 39
+ym	 39
+uma	 39
+_pu	 39
+par	 39
+kay	 39
+n.	 38
+qa,_	 38
+n._	 38
+sus	 38
+aypi	 38
+usqa	 38
+qanku	 38
+ill	 38
+qa,	 38
+was	 38
+pa,	 38
+pa,_	 38
+asp	 38
+qa._	 37
+_mu	 37
+paj	 37
+amp	 37
+hin	 37
+uti	 37
+rin	 37
+_im	 37
+_ima	 37
+ja	 37
+_ri	 37
+rqa_	 37
+taq_	 37
+qa.	 37
+sh	 36
+spa,_	 36
+cha_	 36
+spa,	 36
+achi	 36
+una_	 36
+rqank	 36
+jt	 36
+K	 36
+amu	 36
+aspa	 35
+_Jesu	 35
+Jesus	 35
+nispa	 35
+ki_	 35
+waw	 35
+ko	 35
+ne	 35
+esus	 35
+int	 35
diff --git a/libtextcat/data/new_fingerprints/lm/romanian.lm b/libtextcat/data/new_fingerprints/lm/romanian.lm
new file mode 100644
index 000000000000..65b8e7554d8e
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/romanian.lm
@@ -0,0 +1,400 @@
+_	 20674
+a	 6376
+e	 5815
+i	 5746
+t	 3396
+r	 3280
+n	 3103
+u	 2835
+s	 2611
+c	 2582
+e_	 2235
+l	 2224
+o	 2149
+a_	 1974
+d	 1629
+m	 1528
+p	 1410
+i_	 1358
+in	 1308
+_c	 1167
+_s	 1118
+_d	 999
+re	 905
+ar	 898
+,	 791
+,_	 786
+_p	 785
+de	 771
+_a	 754
+te	 687
+_i	 667
+at	 654
+ti	 645
+ca	 639
+n_	 630
+ta	 617
+si	 614
+_de	 609
+f	 606
+st	 583
+ri	 581
+u_	 567
+nt	 553
+.	 542
+ra	 540
+_m	 534
+g	 528
+v	 516
+ul	 516
+de_	 513
+_in	 503
+b	 492
+_de_	 474
+._	 472
+le	 459
+l_	 444
+un	 443
+_si	 440
+es	 437
+tr	 426
+ea	 420
+t_	 412
+ce	 412
+ma	 407
+cu	 402
+er	 398
+_ca	 397
+si_	 388
+_f	 387
+_l	 383
+z	 382
+la	 381
+ne	 370
+sa	 364
+as	 360
+_e	 357
+in_	 356
+an	 352
+it	 351
+te_	 346
+or	 345
+el	 345
+ci	 339
+_si_	 333
+_n	 330
+are	 324
+pe	 319
+re_	 317
+al	 310
+_t	 309
+se	 304
+ic	 295
+ie	 290
+_u	 290
+ul_	 290
+ni	 289
+int	 285
+_o	 280
+en	 279
+ta_	 279
+ur	 261
+pa	 256
+co	 255
+_pe	 254
+ia	 252
+mi	 251
+pr	 249
+_ma	 249
+oa	 249
+me	 246
+lu	 246
+li	 241
+im	 238
+_in_	 237
+da	 237
+na	 237
+_sa	 235
+ac	 234
+-	 234
+ii	 232
+est	 231
+r_	 231
+h	 230
+_cu	 230
+le_	 229
+ai	 229
+ca_	 227
+il	 226
+ru	 223
+sc	 223
+_v	 221
+nu	 220
+tu	 220
+_un	 220
+nd	 220
+di	 219
+are_	 216
+to	 215
+am	 214
+on	 213
+o_	 208
+is	 208
+sa_	 203
+la_	 200
+_b	 200
+ste	 195
+et	 194
+ec	 191
+_r	 186
+car	 185
+ui	 180
+un_	 179
+lo	 178
+cu_	 177
+ei	 176
+e,	 175
+e,_	 175
+pe_	 171
+m_	 167
+_la	 166
+a,	 165
+a,_	 164
+_ce	 164
+rt	 163
+_co	 163
+ent	 162
+ro	 162
+ele	 162
+_pe_	 160
+po	 160
+ea_	 159
+"	 158
+ntr	 158
+_cu_	 158
+_pr	 157
+ut	 157
+nc	 156
+ata	 155
+care	 154
+um	 153
+au	 151
+va	 151
+_o_	 150
+_car	 150
+ii_	 145
+ind	 145
+_un_	 144
+os	 144
+ad	 141
+_la_	 140
+I	 140
+este	 138
+ste_	 138
+care_	 138
+ir	 137
+ga	 136
+ap	 136
+ol	 136
+ra_	 136
+_di	 134
+D	 134
+_care	 133
+se_	 133
+om	 133
+ara	 133
+ati	 133
+fi	 133
+_sa_	 131
+zi	 130
+vi	 130
+_ca_	 129
+_se	 128
+_nu	 128
+ai_	 127
+ch	 127
+pi	 124
+ve	 123
+fa	 122
+ot	 121
+_a_	 120
+este_	 120
+du	 119
+ine	 119
+s_	 118
+fo	 118
+_ci	 118
+ui_	 118
+ba	 118
+i,	 117
+i,_	 116
+ne_	 115
+us	 115
+_g	 115
+a.	 115
+fe	 114
+A	 114
+pu	 114
+ce_	 113
+ar_	 113
+_pa	 113
+oc	 112
+sta	 112
+lui	 112
+ns	 112
+em	 112
+'	 112
+oar	 112
+din	 111
+iu	 111
+_int	 111
+ate	 111
+mu	 111
+hi	 110
+ele_	 110
+mp	 109
+_D	 109
+S	 109
+sti	 108
+bi	 108
+ata_	 107
+ti_	 107
+tra	 107
+C	 107
+c_	 106
+tre	 106
+_al	 105
+rea	 105
+mai	 105
+j	 104
+a._	 104
+gi	 104
+e.	 103
+d_	 103
+_fa	 103
+E	 102
+mo	 102
+at_	 101
+_e_	 101
+nte	 101
+lt	 101
+sp	 101
+za	 100
+mai_	 100
+su	 99
+na_	 98
+tat	 97
+sin	 97
+ez	 96
+tru	 96
+e._	 96
+ie_	 96
+ia_	 96
+_re	 96
+tul	 96
+_fo	 96
+ina	 95
+art	 95
+_C	 95
+no	 95
+nu_	 94
+_es	 94
+_po	 94
+cr	 94
+inc	 93
+_da	 92
+_mai	 92
+lui_	 92
+_din	 92
+_est	 92
+pre	 91
+_mai_	 91
+io	 91
+chi	 91
+ge	 90
+pri	 90
+eu	 90
+uri	 90
+az	 90
+_nu_	 89
+_me	 89
+ct	 89
+au_	 88
+esc	 88
+ev	 88
+ei_	 88
+min	 87
+ace	 87
+op	 86
+ng	 86
+ici	 86
+_lu	 85
+ari	 85
+_mi	 84
+ita	 84
+_S	 84
+_tr	 84
+ere	 83
+or_	 83
+ast	 83
+ist	 83
+nt_	 83
+_se_	 82
+ou	 82
+tin	 82
+intr	 82
+con	 82
+do	 81
+_fi	 81
+str	 81
+am_	 80
+rat	 80
+ru_	 80
+ri_	 80
+par	 80
+oi	 80
+uc	 79
+ze	 79
+pl	 79
+res	 78
+_ac	 77
+ulu	 77
+din_	 76
+va_	 76
+ada	 76
+ului	 75
+_con	 75
+id	 75
+inte	 74
+ile	 73
+cit	 73
+_din_	 73
+lor	 73
+_"	 72
+ig	 72
+rin	 72
+da_	 72
+_st	 72
+-_	 71
+_-	 71
+it_	 71
+ani	 71
+nd_	 71
+ci_	 70
+ag	 70
+eri	 70
+i.	 70
+tru_	 70
+_ne	 70
+rm	 70
+P	 69
+_este	 69
+nta	 69
+bu	 69
+une	 69
+ma_	 69
+nti	 69
+imp	 68
+_-_	 68
+iv	 68
+ind_	 68
diff --git a/libtextcat/data/new_fingerprints/lm/romansh.lm b/libtextcat/data/new_fingerprints/lm/romansh.lm
new file mode 100644
index 000000000000..e65969ca34fa
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/romansh.lm
@@ -0,0 +1,400 @@
+_	 10888
+a	 3490
+e	 2268
+i	 2196
+s	 2169
+n	 1961
+t	 1555
+r	 1510
+l	 1281
+u	 1249
+a_	 1155
+c	 1060
+d	 954
+o	 815
+s_	 744
+g	 726
+m	 686
+h	 620
+p	 617
+n_	 559
+v	 493
+_s	 480
+er	 476
+ch	 469
+_d	 457
+in	 455
+da	 418
+_c	 404
+r_	 388
+_e	 377
+.	 358
+_p	 340
+as	 333
+l_	 328
+,	 327
+._	 320
+_i	 320
+,_	 315
+la	 313
+en	 312
+sc	 310
+an	 301
+ta	 300
+_da	 285
+f	 282
+_t	 268
+_a	 262
+nt	 259
+_m	 252
+un	 248
+ra	 247
+i_	 247
+na	 245
+ma	 245
+ia	 241
+ar	 234
+sch	 228
+b	 228
+da_	 217
+es	 214
+ai	 213
+st	 212
+'	 209
+e_	 208
+as_	 208
+er_	 200
+t_	 199
+re	 199
+_l	 195
+al	 193
+_n	 193
+el	 192
+tg	 192
+te	 188
+z	 187
+ha	 180
+_f	 180
+sa	 174
+_da_	 172
+ve	 169
+ei	 168
+_v	 165
+at	 165
+ss	 161
+is	 161
+_ch	 161
+on	 160
+la_	 158
+cu	 158
+ad	 158
+he	 156
+in_	 147
+va	 147
+_in	 146
+gl	 145
+ns	 141
+ur	 140
+ü	 140
+u_	 138
+ts	 138
+pe	 136
+li	 134
+gi	 133
+et	 133
+de	 132
+ig	 132
+or	 130
+ti	 129
+il	 127
+d_	 126
+che	 123
+ut	 122
+us	 122
+cha	 121
+di	 120
+ia_	 120
+_b	 118
+_la	 117
+na_	 116
+ain	 115
+per	 115
+to	 115
+_cu	 113
+_sc	 112
+se	 111
+ls	 109
+-	 108
+iu	 108
+ca	 107
+si	 104
+ir	 102
+rt	 102
+ie	 102
+_g	 102
+un_	 102
+nd	 101
+av	 101
+ni	 100
+q	 99
+au	 97
+ls_	 97
+ll	 96
+qu	 96
+_pe	 96
+le	 96
+rs	 95
+pa	 95
+ri	 95
+_ma	 94
+_per	 93
+am	 93
+eg	 92
+_r	 92
+gn	 92
+me	 92
+pi	 91
+an_	 91
+en_	 91
+ga	 91
+ent	 90
+hi	 90
+_e_	 90
+it	 89
+ta_	 88
+ter	 87
+ns_	 86
+iv	 86
+igl	 86
+a.	 85
+em	 85
+I	 85
+chi	 84
+_en	 84
+int	 84
+ue	 83
+su	 82
+tt	 82
+a,	 82
+a,_	 82
+o_	 82
+_ve	 82
+a._	 82
+_q	 81
+_qu	 80
+ge	 80
+"	 80
+_la_	 80
+ar_	 80
+vi	 79
+gl_	 79
+tu	 78
+ng	 78
+ro	 76
+mi	 76
+sta	 75
+ed	 75
+lla	 74
+ei_	 73
+_o	 73
+ic	 73
+el_	 73
+_il	 73
+_in_	 72
+g_	 72
+pr	 71
+nu	 70
+ina	 70
+_h	 69
+scha	 68
+mai	 68
+pl	 68
+il_	 68
+os	 68
+ha_	 68
+be	 67
+uo	 67
+cun	 67
+ra_	 67
+_pa	 65
+ts_	 64
+s.	 64
+co	 64
+_u	 64
+fi	 64
+_I	 63
+sa_	 63
+s._	 63
+_re	 62
+ün	 62
+_nu	 62
+?	 62
+S	 62
+_se	 61
+no	 61
+nt_	 61
+E	 61
+tr	 61
+mp	 60
+igl_	 60
+_su	 60
+_st	 60
+ess	 60
+im	 60
+zi	 59
+?_	 59
+nc	 59
+_E	 58
+_-	 58
+_cun	 58
+_te	 58
+_sa	 58
+ant	 58
+main	 58
+eu	 57
+ssa	 57
+-_	 57
+iun	 57
+_-_	 57
+aint	 56
+op	 56
+al_	 56
+dal	 56
+j	 56
+ama	 55
+_tg	 55
+ua	 55
+M	 55
+per_	 55
+tsc	 54
+nta	 54
+tsch	 54
+um	 54
+fa	 54
+za	 54
+_di	 54
+pia	 54
+_per_	 54
+T	 54
+_M	 53
+ne	 53
+era	 53
+A	 53
+que	 53
+_dal	 53
+cr	 53
+_de	 53
+lla_	 53
+_che	 52
+h'	 52
+_me	 51
+ot	 51
+_pr	 51
+_pl	 51
+_sch	 51
+ch'	 50
+_S	 50
+opi	 50
+ou	 50
+tta	 50
+mo	 50
+ada	 50
+ba	 50
+_an	 49
+top	 49
+id	 49
+è	 49
+he_	 49
+C	 49
+va_	 49
+uto	 49
+ins	 48
+topi	 48
+L	 48
+ir_	 48
+ist	 48
+c_	 48
+_il_	 48
+P	 48
+ss_	 48
+ag	 47
+_no	 47
+res	 47
+las	 47
+_vi	 46
+s,	 46
+schi	 46
+_en_	 46
+tg_	 46
+s,_	 46
+_si	 46
+_que	 45
+_T	 45
+az	 45
+'i	 45
+cun_	 44
+_fa	 44
+_mi	 44
+utop	 44
+utopi	 44
+sche	 44
+_C	 44
+ur_	 44
+tge	 44
+po	 44
+es_	 44
+x	 44
+nz	 44
+_L	 44
+_cun_	 44
+man	 44
+_ch'	 43
+_fi	 43
+pu	 43
+ell	 43
+opia	 43
+_igl	 43
+_ig	 43
+sp	 43
+topia	 43
+ava	 42
+egn	 42
+che_	 42
+on_	 42
+ci	 42
+_P	 42
+ev	 42
+ond	 41
+_"	 41
+à	 41
+us_	 41
+_ha	 41
+D	 40
+_co	 40
+etg	 40
+'e	 40
+las_	 40
+est	 40
+ura	 40
+uel	 39
+ed_	 39
+vo	 39
+gia	 39
+bu	 39
+mu	 39
+nn	 39
+gli	 39
+_A	 39
+lu	 39
+cha_	 39
+ul	 38
+mal	 38
+_ün	 38
+ina_	 38
+_bu	 38
+_ca	 38
+_ü	 38
+uc	 38
+nts	 38
+tra	 38
+_tu	 37
diff --git a/libtextcat/data/new_fingerprints/lm/russian.lm b/libtextcat/data/new_fingerprints/lm/russian.lm
new file mode 100644
index 000000000000..bddb68514275
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/russian.lm
@@ -0,0 +1,400 @@
+_	 76249
+о	 19732
+е	 16714
+а	 14389
+и	 13942
+т	 13160
+н	 12444
+с	 9867
+р	 8461
+в	 7895
+л	 7330
+к	 6498
+м	 5935
+.	 5725
+у	 5287
+д	 5019
+п	 4877
+я	 4083
+,	 3899
+,_	 3878
+ы	 3656
+ь	 3376
+и_	 3167
+_п	 3144
+е_	 3135
+о_	 3098
+-	 3019
+з	 2983
+_в	 2952
+._	 2930
+_с	 2919
+ч	 2887
+г	 2876
+б	 2797
+ст	 2672
+_н	 2631
+то	 2585
+..	 2407
+_и	 2316
+но	 2300
+-_	 2294
+й	 2281
+а_	 2249
+на	 2057
+я_	 2029
+ов	 1981
+ни	 1950
+_т	 1944
+х	 1874
+ен	 1856
+_о	 1774
+...	 1744
+ра	 1709
+не	 1685
+по	 1636
+_-	 1625
+ко	 1616
+те	 1595
+ро	 1584
+_к	 1558
+_-_	 1531
+й_	 1521
+ет	 1518
+ж	 1509
+_и_	 1454
+та	 1433
+ан	 1419
+ер	 1396
+от	 1389
+ь_	 1381
+го	 1375
+ал	 1370
+_по	 1364
+ре	 1345
+ка	 1338
+пр	 1337
+ва	 1329
+ти	 1306
+ли	 1300
+_д	 1297
+_м	 1290
+ес	 1284
+во	 1271
+че	 1256
+ор	 1245
+....	 1232
+ть	 1219
+ос	 1212
+ш	 1192
+ю	 1187
+в_	 1168
+.....	 1167
+он	 1147
+ак	 1144
+ц	 1109
+ог	 1101
+ло	 1099
+т_	 1093
+ри	 1076
+м_	 1074
+_пр	 1063
+ол	 1062
+ль	 1045
+_не	 1034
+ел	 1029
+_б	 1026
+ин	 1000
+од	 998
+ом	 996
+ме	 993
+ы_	 975
+ве	 968
+ск	 968
+_на	 966
+де	 946
+ны	 943
+_р	 931
+_ч	 923
+ат	 913
+ем	 910
+у_	 907
+за	 898
+х_	 898
+ле	 889
+то_	 881
+ит	 878
+ой	 875
+се	 862
+_в_	 833
+_з	 816
+ки	 816
+тр	 807
+"	 786
+ть_	 769
+ед	 767
+не_	 762
+ся	 754
+ла	 748
+об	 747
+мо	 741
+да	 730
+го_	 715
+к_	 713
+ис	 711
+_у	 702
+ой_	 697
+ил	 694
+ма	 692
+нн	 687
+до	 662
+ас	 660
+ам	 656
+ия	 649
+же	 646
+аз	 638
+со	 629
+на_	 619
+_г	 615
+ми	 612
+_а	 610
+э	 609
+вс	 608
+.._	 605
+вы	 604
+ого	 604
+им	 604
+_ко	 600
+ав	 597
+сл	 594
+ие	 593
+_не_	 589
+_е	 587
+_те	 583
+ту	 583
+ич	 583
+ру	 575
+ост	 571
+щ	 571
+л_	 570
+_э	 569
+_я	 559
+А	 556
+ени	 544
+из	 540
+ек	 536
+ова	 533
+ф	 525
+:	 519
+В	 513
+ани	 511
+_вс	 510
+ий	 510
+Н	 508
+_ка	 508
+!	 503
+?	 501
+ди	 498
+ли_	 489
+П	 488
+про	 486
+_ра	 485
+си	 484
+ир	 484
+_ст	 484
+ьн	 484
+льн	 484
+:_	 484
+ся_	 480
+_за	 477
+бо	 470
+_л	 469
+..._	 465
+бы	 464
+их	 464
+И	 462
+ег	 461
+тв	 459
+ния	 458
+ят	 454
+чт	 454
+эт	 445
+чес	 442
+_то	 442
+ия_	 441
+ик	 440
+ви	 437
+ак_	 436
+ста	 436
+ого_	 435
+_В	 434
+иче	 433
+ци	 431
+что	 431
+ых	 429
+_эт	 429
+С	 425
+_чт	 424
+_А	 424
+ю_	 423
+пе	 422
+ня	 422
+_что	 422
+ля	 419
+все	 418
+ду	 418
+еск	 415
+нт	 413
+как	 411
+сто	 411
+_вы	 409
+ну	 408
+тс	 406
+н_	 406
+_П	 401
+М	 401
+но_	 399
+_про	 398
+_.	 397
+ров	 396
+це	 396
+кт	 394
+ест	 394
+_"	 393
+ше	 393
+с_	 392
+_от	 392
+О	 391
+_на_	 391
+ред	 391
+ческ	 390
+о-	 390
+ван	 388
+а,	 385
+ад	 384
+ая	 384
+_я_	 383
+а,_	 383
+ты	 383
+?_	 383
+_об	 380
+_все	 380
+_та	 378
+_как	 376
+хо	 375
+так	 375
+аль	 374
+ож	 373
+ых_	 372
+ово	 372
+ив	 371
+_во	 369
+му	 369
+_Н	 369
+ей	 368
+пре	 368
+зн	 366
+ичес	 365
+пи	 365
+его	 362
+_со	 360
+ое	 360
+!_	 360
+ать	 360
+сти	 358
+их_	 358
+тн	 358
+мен	 358
+тся	 356
+ие_	 356
+ическ	 354
+бе	 352
+_бы	 352
+стр	 349
+ку	 349
+_мо	 348
+ет_	 348
+Т	 346
+_ме	 344
+ев	 344
+при	 343
+чи	 342
+мн	 341
+ния_	 339
+ар	 338
+нно	 337
+ован	 334
+кс	 334
+ур	 328
+_че	 328
+оль	 328
+ут	 327
+что_	 324
+ом_	 323
+оп	 323
+рм	 322
+А_	 322
+_что_	 322
+это	 322
+оч	 321
+о,_	 320
+о,	 320
+ско	 319
+кон	 319
+лов	 318
+ый	 318
+ус	 317
+от_	 316
+иро	 315
+ств	 314
+и,	 314
+ий_	 313
+сс	 313
+и,_	 313
+том	 312
+ае	 312
+енн	 311
+ез	 311
+ной	 311
+_это	 310
+К	 309
+са	 309
+раз	 309
+еп	 309
+_до	 308
+оло	 308
+сть	 308
+уд	 307
+дел	 307
+_И	 305
+аб	 305
+сь	 303
+альн	 302
+ок	 300
+ски	 300
+ных	 300
+_при	 298
+ча	 297
+_ж	 297
+е,	 297
+е,_	 297
+_А_	 296
+_ни	 296
+_._	 295
+тся_	 295
+ии	 294
+зна	 293
+я,	 292
+я,_	 292
+_пре	 291
+_С	 290
+ной_	 290
+ая_	 288
+_О	 288
+али	 286
+же_	 285
+сп	 285
+ист	 285
+ных_	 285
+з_	 283
+_М	 283
diff --git a/libtextcat/data/new_fingerprints/lm/sanskrit.lm b/libtextcat/data/new_fingerprints/lm/sanskrit.lm
new file mode 100644
index 000000000000..e21b8712111d
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/sanskrit.lm
@@ -0,0 +1,400 @@
+a	 15017
+_	 14975
+h	 5028
+i	 3820
+t	 2976
+s	 2788
+r	 2599
+|	 2437
+n	 2432
+aa	 2276
+ha	 2007
+m	 1982
+a_	 1802
+v	 1799
+d	 1768
+u	 1629
+y	 1599
+_|	 1470
+|_	 1470
+e	 1403
+k	 1371
+sh	 1330
+ra	 1243
+p	 1213
+va	 1152
+A	 1134
+ya	 1120
+ma	 1097
+na	 1091
+ar	 1080
+ta	 1054
+M	 1050
+.	 1047
+am	 1037
+an	 1006
+||	 967
+||_	 965
+_||	 965
+_||_	 963
+at	 962
+M_	 946
+as	 910
+_s	 882
+o	 848
+b	 844
+i_	 827
+aM	 764
+aM_	 685
+c	 630
+ch	 629
+sa	 623
+N	 616
+ad	 612
+H	 601
+pa	 595
+H_	 584
+g	 580
+_n	 579
+l	 554
+bh	 552
+hi	 547
+ka	 542
+it	 536
+ii	 535
+ama	 519
+_|_	 505
+e_	 477
+_p	 475
+dh	 475
+av	 469
+ak	 445
+aH	 444
+da	 440
+aH_	 439
+ay	 437
+j	 437
+_na	 432
+ana	 430
+hh	 428
+ti	 426
+ara	 425
+aa_	 410
+_k	 394
+shh	 389
+_v	 388
+_sa	 381
+.h	 379
+ah	 369
+_b	 368
+h_	 363
+.h_	 363
+cha	 362
+haa	 361
+_t	 358
+ri	 352
+sha	 345
+ap	 333
+vi	 330
+is	 329
+^	 321
+o_	 321
+_m	 320
+ai	 311
+_d	 311
+la	 302
+na_	 301
+.n	 298
+ava	 295
+al	 294
+_sh	 291
+ja	 288
+a.	 280
+aan	 277
+ish	 274
+aN	 273
+aya	 273
+ash	 266
+ha_	 265
+ga	 264
+st	 255
+ni	 255
+ii_	 254
+hu	 253
+Na	 253
+R	 248
+R^	 248
+^i	 247
+R^i	 247
+a.n	 243
+th	 241
+_c	 240
+_ch	 239
+maa	 238
+bha	 237
+vaa	 233
+ab	 228
+ir	 226
+\	 226
+ita	 223
+uu	 222
+dha	 220
+har	 218
+_a	 216
+_bh	 216
+nam	 212
+u_	 212
+he	 212
+m.h_	 211
+m.	 211
+m.h	 211
+ur	 210
+es	 209
+ata	 208
+te	 206
+yaa	 205
+_ma	 204
+esh	 202
+aka	 200
+id	 199
+pr	 199
+aha	 198
+hy	 198
+T	 197
+aat	 197
+_OM_	 196
+OM	 196
+_O	 196
+_OM	 196
+OM_	 196
+O	 196
+ti_	 195
+ari	 194
+raa	 193
+ag	 192
+_y	 192
+aas	 190
+_ta	 190
+_j	 189
+I	 189
+_na_	 187
+am.h_	 185
+am.h	 185
+am.	 185
+_pa	 183
+iv	 182
+de	 182
+ada	 178
+nd	 178
+_cha	 177
+_h	 176
+ati	 175
+taa	 173
+ev	 172
+nt	 171
+rii	 171
+ishh	 170
+ya_	 168
+_vi	 166
+ast	 165
+tr	 164
+abh	 164
+kh	 162
+ala	 160
+tha	 160
+apa	 160
+asa	 158
+naa	 158
+_nam	 156
+ru	 156
+A_	 155
+_ka	 154
+aar	 153
+_pr	 152
+_g	 151
+pra	 150
+ham	 150
+hha	 149
+aana	 149
+di	 149
+ra_	 147
+ik	 146
+.a	 144
+yat	 143
+ks	 143
+hA	 143
+hya	 143
+ksh	 143
+ut	 142
+sy	 141
+nama	 140
+_va	 140
+.\	 140
+paa	 140
+han	 139
+eva	 138
+U	 138
+mi	 138
+_r	 136
+_ja	 136
+asy	 135
+hr	 135
+sya	 134
+cha_	 132
+rv	 132
+tv	 130
+asya	 130
+kar	 130
+ho	 129
+yo	 129
+in	 128
+adh	 127
+yA	 127
+va_	 126
+su	 125
+_ya	 125
+shha	 124
+pu	 124
+R^it	 123
+sta	 123
+mu	 123
+^it	 123
+ty	 123
+_nama	 121
+ac	 120
+rii_	 120
+ach	 120
+aNa	 119
+tas	 119
+shi	 119
+iva	 119
+hav	 119
+tra	 118
+var	 118
+par	 118
+haM	 117
+aad	 117
+kaa	 117
+hch	 117
+mas	 117
+ai_	 117
+hc	 117
+sar	 116
+aam	 116
+_bha	 115
+_pra	 114
+et	 114
+haM_	 113
+aay	 113
+aj	 113
+ye	 113
+o.	 113
+An	 111
+arii	 111
+t.h	 110
+t.	 110
+ath	 110
+t.h_	 109
+man	 109
+te_	 108
+o.a	 108
+hara	 108
+rA	 108
+rva	 108
+tva	 108
+asta	 108
+up	 108
+shr	 107
+daa	 104
+me	 104
+dr	 104
+ram	 104
+arii_	 102
+_ni	 102
+arv	 102
+iH	 102
+hit	 101
+ras	 101
+aga	 101
+Am	 101
+mA	 101
+ba	 101
+amas	 100
+tu	 100
+yaM	 100
+ant	 99
+ud	 99
+uk	 98
+iH_	 98
+yaM_	 98
+kha	 98
+au	 98
+ira	 97
+shhT	 97
+rah	 97
+hT	 97
+hhT	 97
+D	 96
+_sar	 96
+re	 96
+eshh	 95
+sarv	 94
+amaa	 94
+and	 94
+arva	 94
+_ra	 93
+_dh	 93
+tt	 92
+tad	 92
+hm	 92
+raM_	 91
+dev	 91
+raM	 91
+C	 91
+ani	 91
+_sarv	 90
+atha	 89
+Ad	 89
+chi	 89
+tA	 88
+sarva	 88
+avi	 88
+taM	 87
+hava	 87
+anaa	 86
+vA	 86
+dd	 86
+nA	 85
+Ar	 85
+hv	 85
+taM_	 85
+dhi	 84
+ksha	 84
+ip	 84
+ma_	 84
+_sha	 84
+ati_	 83
+yai	 83
+vat	 83
+At	 83
+kR	 82
+kR^	 82
+bhi	 82
+_shr	 82
+to	 82
+ta_	 82
+br	 82
+ek	 82
+kR^i	 82
+tat	 81
+nta	 81
+hma	 81
+aaya	 80
+tam	 80
+en	 80
+us	 79
+bra	 79
+ke	 79
+kt	 79
+ddh	 79
+mo	 79
diff --git a/libtextcat/data/new_fingerprints/lm/scots.lm b/libtextcat/data/new_fingerprints/lm/scots.lm
new file mode 100644
index 000000000000..7aac457075f6
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/scots.lm
@@ -0,0 +1,400 @@
+_	 11688
+e	 3223
+a	 2469
+t	 2269
+i	 1928
+n	 1903
+r	 1414
+o	 1406
+h	 1369
+s	 1249
+l	 929
+n_	 890
+_t	 862
+_a	 843
+d	 818
+e_	 798
+th	 704
+w	 661
+he	 625
+an	 612
+t_	 606
+u	 592
+_th	 575
+c	 508
+s_	 471
+the	 470
+,	 469
+-	 458
+in	 455
+m	 445
+,_	 440
+b	 434
+g	 429
+er	 409
+ee	 408
+_the	 407
+k	 402
+an_	 402
+f	 385
+_w	 378
+he_	 376
+the_	 364
+_an	 362
+_o	 360
+y	 358
+_the_	 354
+_s	 353
+_an_	 342
+a_	 335
+r_	 327
+_b	 316
+d_	 303
+i_	 278
+en	 277
+p	 270
+ei	 245
+A	 236
+wa	 232
+_A	 231
+re	 229
+in_	 229
+ui	 218
+oo	 217
+le	 217
+ai	 216
+et	 212
+ti	 209
+it	 209
+_f	 206
+te	 204
+_a_	 203
+_m	 202
+ha	 200
+as	 193
+on	 188
+at	 184
+_i	 183
+_wa	 183
+_c	 182
+o_	 180
+or	 178
+_h	 176
+_g	 169
+ch	 165
+A_	 159
+_l	 158
+_A_	 157
+st	 156
+_d	 155
+_ti	 148
+.	 148
+._	 146
+ke	 144
+ti_	 143
+--	 143
+_o_	 142
+ow	 142
+---	 140
+ed	 138
+----	 138
+_r	 137
+as_	 137
+y_	 136
+er_	 136
+-----	 136
+ir	 135
+aa	 135
+la	 131
+een	 130
+ae	 129
+_ti_	 128
+ra	 126
+es	 125
+nd	 124
+de	 120
+h_	 120
+ie	 120
+ar	 119
+ll	 119
+nt	 118
+ot	 118
+en_	 115
+ma	 115
+eet	 113
+her	 112
+el	 112
+is	 112
+'	 112
+at_	 111
+ic	 109
+se	 108
+or_	 106
+wu	 104
+me	 104
+ne	 103
+fo	 102
+on_	 101
+was	 99
+_was	 98
+et_	 98
+ri	 98
+_e	 97
+_ma	 97
+v	 97
+_n	 97
+!	 97
+li	 97
+ht	 93
+hi	 92
+_wu	 92
+ng	 91
+ro	 91
+it_	 90
+ck	 90
+_fo	 90
+tha	 90
+k_	 89
+il	 89
+cht	 86
+eet_	 86
+_p	 86
+we	 86
+_was_	 85
+was_	 85
+rt	 84
+ed_	 83
+ter	 83
+id	 83
+ga	 82
+;	 82
+;_	 81
+ther	 79
+tt	 76
+air	 76
+e,	 75
+un	 75
+ho	 75
+for	 74
+ge	 74
+_st	 73
+_y	 72
+_he	 72
+wh	 71
+_on	 71
+sh	 70
+z	 70
+e,_	 69
+bi	 68
+_tha	 68
+wui	 67
+!_	 67
+ad	 67
+een_	 66
+l_	 66
+ts	 66
+_for	 66
+n,	 66
+_wh	 65
+re_	 65
+be	 65
+eh	 64
+hat	 64
+ns	 64
+br	 64
+g_	 64
+ui_	 64
+rr	 64
+wui_	 63
+ni	 63
+_wui	 62
+ay	 62
+s,	 62
+pe	 61
+n,_	 61
+bo	 61
+al	 61
+ye	 61
+_bi	 60
+oot	 60
+na	 60
+ang	 60
+s,_	 59
+es_	 59
+ill	 58
+that	 58
+_wui_	 58
+nn	 58
+eh_	 58
+oa	 57
+han	 57
+_that	 56
+_br	 56
+ca	 56
+_ga	 56
+ng_	 56
+um	 55
+hat_	 55
+oon	 55
+od	 55
+for_	 55
+no	 55
+ree	 55
+_for_	 54
+_le	 54
+ht_	 54
+ot_	 54
+_k	 53
+rd	 53
+ki	 53
+aw	 53
+nd_	 53
+_on_	 53
+_it	 53
+ik	 53
+t,	 53
+_be	 52
+that_	 52
+ve	 52
+rn	 52
+'s	 51
+au	 51
+co	 51
+ich	 51
+to	 51
+lo	 51
+t,_	 51
+ea	 51
+tee	 51
+lan	 50
+fi	 50
+_at	 50
+am	 50
+_in	 50
+ere	 50
+ur	 50
+le_	 50
+nt_	 49
+'s_	 49
+hin	 49
+yi	 49
+hr	 49
+ts_	 49
+_ca	 48
+"	 48
+ta	 48
+cht_	 48
+-_	 48
+_as	 47
+T	 47
+ang_	 47
+lei	 46
+_ma_	 46
+tr	 46
+_ro	 46
+fe	 46
+ma_	 46
+icht	 46
+_as_	 46
+der	 46
+cl	 46
+e-	 45
+n-	 45
+thr	 45
+ba	 45
+m_	 45
+st_	 45
+rt_	 45
+_u	 45
+do	 45
+_T	 45
+im	 44
+_se	 44
+sk	 44
+_la	 44
+eik	 44
+bit	 43
+ike	 43
+B	 43
+kee	 43
+tte	 43
+di	 43
+eed	 43
+_B	 42
+_aa	 42
+her_	 42
+da	 42
+ff	 42
+tu	 42
+ie_	 42
+_cl	 42
+_ba	 42
+oot_	 42
+bu	 41
+eike	 41
+oc	 41
+hu	 41
+_thr	 41
+ther_	 41
+_co	 41
+aa_	 41
+so	 41
+_me	 41
+H	 41
+_H	 40
+ke_	 40
+ert	 40
+lu	 40
+ist	 40
+si	 40
+iz	 40
+ar_	 39
+uc	 39
+thi	 39
+ad_	 39
+ru	 39
+owe	 39
+gi	 38
+_bit	 38
+_do	 38
+int	 38
+bl	 38
+ld	 38
+_at_	 38
+lt	 38
+ac	 38
+_ha	 38
+ae_	 38
+rs	 37
+here	 37
+ei_	 37
+han_	 37
+p_	 37
+is_	 37
+eth	 37
+fa	 37
+_sk	 37
+ll_	 37
+ss	 36
+bra	 36
+wha	 36
+gl	 36
+ck_	 36
+pl	 36
+lin	 36
+ir_	 36
+ab	 36
+_ther	 36
+_da	 35
+ce	 35
+rin	 35
+_oo	 35
+rl	 35
+wee	 35
+and	 35
+sa	 35
+_yi	 35
+_bra	 35
+'d	 35
+ds	 35
+_bo	 35
diff --git a/libtextcat/data/new_fingerprints/lm/scots_gaelic.lm b/libtextcat/data/new_fingerprints/lm/scots_gaelic.lm
new file mode 100644
index 000000000000..491862a8c9d2
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/scots_gaelic.lm
@@ -0,0 +1,400 @@
+_	 12634
+a	 5353
+h	 3268
+i	 2898
+n	 2792
+e	 1651
+r	 1563
+d	 1455
+_a	 1425
+c	 1245
+n_	 1236
+s	 1165
+l	 1152
+an	 1121
+t	 980
+ai	 979
+g	 962
+u	 905
+ch	 902
+ha	 836
+h_	 833
+a_	 829
+ea	 821
+o	 794
+dh	 726
+an_	 711
+b	 639
+m	 585
+na	 514
+nn	 506
+ac	 498
+r_	 495
+s_	 482
+ir	 480
+ach	 466
+id	 458
+_an	 450
+_c	 427
+th	 403
+à	 388
+he	 383
+in	 379
+bh	 367
+idh	 358
+ad	 342
+_n	 341
+il	 332
+nn_	 323
+_t	 322
+_d	 319
+ar	 317
+e_	 311
+dh_	 307
+_an_	 303
+_b	 302
+_na	 294
+air	 289
+ig	 279
+.	 275
+ir_	 272
+ag	 272
+_ai	 272
+,	 270
+gu	 269
+,_	 269
+._	 265
+ean	 264
+ch_	 261
+f	 259
+?	 258
+_s	 255
+ann	 250
+ra	 241
+ei	 241
+_a_	 241
+ha_	 241
+d_	 238
+-	 235
+_m	 231
+gh	 230
+hea	 228
+le	 226
+_f	 224
+ui	 223
+is	 223
+as	 218
+adh	 218
+l_	 216
+g_	 208
+ài	 207
+ò	 207
+hai	 205
+cha	 205
+air_	 204
+na_	 201
+inn	 198
+tha	 190
+C	 189
+G	 188
+ann_	 187
+_ag	 186
+_air	 186
+eac	 185
+_g	 185
+_na_	 184
+ach_	 184
+_C	 183
+us	 183
+_ch	 183
+la	 182
+_G	 182
+each	 181
+us_	 178
+al	 178
+gus	 176
+gus_	 176
+_th	 169
+_air_	 168
+_agus	 167
+agus_	 167
+_agu	 167
+agus	 167
+agu	 167
+ta	 164
+aid	 163
+hi	 163
+hd	 163
+chd	 160
+T	 157
+A	 156
+ic	 152
+_T	 152
+adh_	 150
+idh_	 148
+mh	 147
+?_	 146
+ar_	 145
+oi	 144
+da	 143
+aidh	 143
+_bh	 139
+ean_	 138
+sa	 138
+ig_	 138
+_r	 136
+_A	 134
+ì	 134
+te	 134
+achd	 131
+hu	 131
+_e	 130
+aig	 130
+_l	 130
+_ann	 129
+ain	 127
+ne	 127
+dhe	 125
+_dh	 125
+àid	 123
+o_	 121
+hl	 119
+acha	 119
+ga	 118
+àidh	 118
+on	 118
+it	 117
+aidh_	 116
+de	 115
+nan	 115
+ua	 115
+_ann_	 115
+ich	 115
+il_	 114
+m_	 114
+eil	 114
+ri	 112
+at	 112
+ma	 111
+li	 109
+ao	 109
+re	 109
+inn_	 108
+_tha	 107
+fh	 106
+as_	 106
+bh_	 106
+nan_	 103
+lea	 103
+lt	 103
+S	 103
+a?	 103
+a?_	 102
+io	 102
+E	 101
+am	 101
+'	 100
+_a?	 100
+igh	 100
+_a?_	 99
+_gu	 99
+idhe	 99
+t_	 99
+se	 99
+si	 98
+ba	 97
+ù	 97
+tha_	 96
+bha	 95
+B	 94
+is_	 94
+u_	 94
+_B	 94
+_i	 93
+ile	 92
+aic	 91
+hei	 91
+ia	 90
+ho	 89
+Th	 88
+ath	 88
+_Th	 88
+rt	 87
+ib	 87
+Gàid	 86
+_Gài	 86
+_Gà	 86
+Gài	 86
+òr	 86
+Gà	 86
+Gàidh	 86
+_Gàid	 86
+had	 85
+ibh	 85
+_fh	 85
+p	 84
+ad_	 83
+_?	 83
+_E	 83
+hd_	 82
+dhea	 82
+chd_	 82
+ear	 81
+ith	 81
+_tha_	 80
+h-	 79
+eal	 78
+hean	 78
+sg	 77
+rea	 77
+_S	 76
+ais	 75
+ll	 75
+han	 74
+hà	 74
+achd_	 74
+ead	 74
+idhea	 73
+am_	 72
+dha	 72
+_nan	 71
+_nan_	 71
+hadh	 71
+gh_	 71
+ail	 70
+hui	 70
+Ch	 69
+eachd	 69
+h.	 69
+aich	 69
+hli	 69
+chai	 69
+om	 68
+fa	 68
+chad	 68
+I	 67
+h._	 67
+_Ch	 67
+tea	 67
+nea	 66
+chadh	 66
+achad	 66
+rai	 66
+lig	 66
+haid	 66
+dea	 66
+rt_	 65
+àr	 65
+dhl	 65
+ana	 64
+eann	 64
+Ei	 64
+le_	 64
+hn	 64
+ilt	 64
+uid	 64
+_fa	 63
+_Tha	 63
+Tha	 63
+ob	 63
+_si	 62
+ro	 62
+cu	 62
+ainn	 62
+un	 62
+dhli	 61
+idhli	 61
+lean	 61
+idhl	 61
+àidhl	 61
+hlig	 61
+dhlig	 61
+in_	 60
+_à	 60
+st	 60
+rr	 60
+_cu	 60
+hr	 60
+_aig	 60
+bhe	 59
+i_	 59
+aigh	 59
+Tha_	 59
+è	 59
+_ri	 59
+_Tha_	 59
+lb	 58
+che	 58
+ran	 58
+nac	 58
+haidh	 58
+hadh_	 58
+aig_	 58
+Gh	 58
+ilea	 58
+_Gh	 58
+lte	 58
+_le	 58
+ru	 58
+àidhe	 57
+_I	 57
+ilte	 57
+eadh	 57
+M	 56
+hlig_	 56
+L	 56
+chu	 56
+nach	 56
+_ma	 56
+lig_	 56
+h,_	 55
+th_	 55
+ibh_	 55
+_aig_	 55
+D	 55
+atha	 55
+_Ei	 55
+h,	 55
+gu_	 54
+_gu_	 54
+im	 54
+eil_	 54
+eu	 53
+_M	 53
+Al	 53
+irt	 53
+_L	 53
+iad	 53
+sea	 52
+lba	 52
+Alba	 52
+F	 52
+Alb	 52
+uai	 52
+ich_	 52
+_F	 51
+ilean	 51
+has	 51
+tai	 51
+each_	 50
+eacha	 50
+har	 50
+ni	 50
+_de	 50
+irt_	 50
+n,_	 50
+mha	 50
+n,	 50
+_e_	 50
+ide	 49
+neach	 49
+neac	 49
+ur	 49
+rd	 49
+_h	 49
+hean_	 49
+oc	 49
+eò	 49
+te_	 49
+han_	 49
+on_	 49
diff --git a/libtextcat/data/new_fingerprints/lm/serbian_ascii.lm b/libtextcat/data/new_fingerprints/lm/serbian_ascii.lm
new file mode 100644
index 000000000000..9471be6eabd5
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/serbian_ascii.lm
@@ -0,0 +1,400 @@
+_	 34122
+a	 9113
+o	 8135
+i	 7736
+e	 7535
+n	 5207
+s	 4860
+j	 3995
+t	 3797
+r	 3660
+u	 3224
+l	 3065
+d	 3061
+e_	 2941
+v	 2786
+a_	 2746
+k	 2701
+m	 2492
+o_	 2328
+y	 2238
+p	 2151
+_s	 2148
+i_	 2094
+je	 1887
+c	 1854
+z	 1731
+_n	 1437
+_p	 1432
+g	 1418
+b	 1368
+u_	 1333
+je_	 1237
+,	 1226
+,_	 1214
+_i	 1130
+st	 1105
+na	 1076
+.	 1056
+_d	 1033
+._	 1030
+_j	 967
+ra	 934
+ko	 908
+ni	 900
+cy	 893
+sy	 875
+_je	 871
+_o	 824
+ta	 799
+no	 780
+_u	 777
+re	 766
+_b	 764
+_k	 763
+da	 760
+ne	 754
+li	 750
+ti	 745
+se	 722
+po	 713
+to	 713
+_je_	 696
+an	 688
+ja	 683
+pr	 665
+va	 651
+lo	 634
+_z	 626
+m_	 625
+is	 625
+il	 622
+ov	 621
+la	 621
+_m	 615
+bi	 604
+_t	 603
+_po	 594
+en	 586
+_se	 578
+os	 578
+in	 576
+od	 576
+ka	 552
+ve	 548
+ij	 538
+_pr	 536
+al	 536
+vo	 535
+om	 530
+_i_	 525
+nj	 515
+ed	 509
+_na	 507
+na_	 503
+og	 499
+oj	 498
+ma	 493
+_bi	 492
+on	 489
+ak	 482
+im	 481
+ye	 481
+ro	 480
+vi	 473
+sa	 469
+ri	 464
+da_	 451
+av	 450
+at	 449
+se_	 447
+es	 446
+h	 443
+ao	 441
+ji	 437
+yi	 436
+_da	 433
+ad	 432
+_se_	 430
+lj	 428
+zy	 426
+za	 426
+_ne	 425
+de	 422
+tr	 417
+cj	 415
+_u_	 414
+_c	 412
+le	 402
+_v	 397
+ar	 390
+_g	 390
+ic	 384
+n_	 382
+ju	 379
+lo_	 377
+aj	 376
+_ko	 369
+ao_	 366
+ek	 361
+_da_	 359
+et	 356
+go	 354
+iz	 346
+_za	 345
+_r	 344
+or	 342
+mo	 341
+el	 340
+as	 339
+ik	 336
+te	 332
+_sa	 329
+d_	 323
+am	 320
+me	 318
+sto	 317
+di	 315
+ec	 311
+ol	 310
+a,_	 307
+a,	 307
+_ni	 302
+ya	 296
+do	 295
+yt	 294
+su	 292
+syt	 289
+li_	 288
+sta	 286
+ije	 284
+ko_	 277
+ti_	 277
+la_	 277
+ga	 276
+bil	 275
+no_	 274
+a.	 273
+nu	 272
+a._	 271
+ne_	 271
+om_	 268
+_cy	 266
+_na_	 263
+_bil	 263
+sv	 263
+ru	 259
+to_	 256
+_od	 253
+cyi	 253
+nje	 251
+it	 251
+pa	 250
+az	 248
+e,_	 245
+e,	 245
+ob	 244
+dn	 243
+ac	 242
+ost	 242
+k_	 240
+iv	 239
+io	 238
+_su	 238
+_iz	 237
+ilo	 235
+_sv	 234
+_ka	 233
+koj	 231
+mi	 229
+im_	 229
+ije_	 227
+g_	 226
+em	 223
+su_	 223
+ih	 223
+ji_	 221
+kr	 220
+ut	 220
+_koj	 220
+V	 218
+_st	 218
+ye_	 217
+_l	 214
+_V	 213
+ovo	 211
+j_	 210
+uc	 208
+ja_	 208
+h_	 207
+nij	 206
+sk	 206
+ot	 203
+io_	 203
+gl	 203
+_do	 201
+ok	 200
+ns	 199
+ilo_	 199
+er	 197
+ih_	 195
+pre	 193
+ci	 193
+og_	 193
+ki	 192
+sl	 191
+t_	 189
+ni_	 189
+_a	 189
+vr	 188
+ati	 187
+_su_	 186
+nije	 181
+pro	 181
+be	 180
+yn	 179
+cye	 178
+ju_	 178
+ku	 177
+isy	 177
+ta_	 174
+sye	 172
+_tr	 172
+O	 172
+jen	 172
+_to	 171
+pi	 168
+_pre	 168
+S	 168
+ima	 167
+nije_	 167
+_mo	 166
+eg	 166
+e._	 164
+za_	 164
+e.	 164
+_pro	 164
+gov	 163
+N	 162
+dr	 162
+ako	 162
+tv	 162
+_S	 160
+P	 159
+ma_	 159
+_on	 159
+sp	 158
+nst	 158
+anj	 158
+dj	 157
+oc	 157
+_sy	 156
+ev	 155
+ce	 155
+lik	 154
+_nij	 153
+_N	 152
+ist	 151
+_P	 151
+_nije	 151
+-	 151
+ba	 150
+jed	 150
+sti	 150
+ova	 149
+_is	 148
+id	 148
+ton	 148
+ke	 147
+pos	 147
+od_	 147
+osy	 146
+Vi	 146
+ila	 145
+ins	 145
+bo	 145
+_Vi	 145
+ir	 144
+_za_	 144
+oz	 144
+ecj	 144
+cje	 143
+on_	 143
+zn	 142
+_O	 141
+us	 141
+i,	 141
+i,_	 141
+mu	 140
+inst	 140
+cya	 140
+oji	 139
+esy	 139
+icy	 139
+lja	 138
+_go	 138
+i.	 138
+_re	 137
+_bilo	 137
+edn	 137
+acy	 137
+rat	 137
+bilo	 137
+ali	 136
+ecy	 136
+ija	 135
+pri	 135
+ad_	 135
+lic	 135
+i._	 135
+Vins	 134
+Vin	 134
+ston	 134
+Vinst	 134
+ga_	 134
+nston	 134
+insto	 134
+nsto	 134
+_Vins	 133
+_Vin	 133
+zi	 132
+ran	 131
+le_	 130
+ili	 130
+bilo_	 130
+_pos	 129
+ila_	 129
+est	 128
+_ve	 128
+tre	 128
+zye	 127
+_nj	 127
+si	 126
+f	 126
+alo	 125
+ako_	 125
+tra	 125
+sa_	 125
+pu	 124
+ud	 124
+z_	 124
+_ra	 124
+iti	 124
+_de	 124
+odi	 123
+T	 123
+-_	 122
+o,_	 121
+o,	 121
+du	 121
+rs	 121
+B	 120
+ka_	 119
+red	 119
+_od_	 118
+an_	 118
+nu_	 118
+iko	 117
+dno	 117
+_pa	 117
+s_	 116
diff --git a/libtextcat/data/new_fingerprints/lm/slovak_ascii.lm b/libtextcat/data/new_fingerprints/lm/slovak_ascii.lm
new file mode 100644
index 000000000000..29c8736b3ba3
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/slovak_ascii.lm
@@ -0,0 +1,400 @@
+_	 20064
+a	 4991
+o	 4983
+e	 3838
+n	 3342
+i	 3317
+r	 2583
+s	 2501
+v	 2383
+t	 2325
+c	 1918
+k	 1912
+l	 1888
+d	 1736
+u	 1725
+p	 1543
+a_	 1527
+y	 1371
+m	 1339
+z	 1227
+h	 1194
+e_	 956
+_p	 881
+_s	 828
+o_	 814
+na	 809
+b	 808
+_v	 798
+j	 797
+.	 796
+ov	 795
+._	 785
+st	 687
+i_	 665
+,	 657
+,_	 657
+_n	 625
+ch	 623
+u_	 618
+ro	 617
+po	 598
+_o	 546
+ne	 529
+en	 520
+v_	 519
+_a	 516
+ra	 506
+pr	 488
+y_	 481
+od	 476
+_z	 467
+ie	 462
+ni	 448
+an	 447
+vy	 434
+to	 433
+h_	 431
+_na	 429
+re	 416
+ch_	 404
+ho	 401
+al	 399
+ci	 394
+va	 387
+na_	 386
+_pr	 385
+_d	 384
+_k	 378
+la	 377
+ko	 375
+do	 374
+_po	 373
+si	 353
+_t	 346
+_r	 337
+os	 336
+no	 334
+in	 328
+tr	 324
+om	 321
+_v_	 320
+ny	 319
+m_	 319
+ri	 317
+S	 306
+ac	 302
+sa	 300
+ti	 300
+_m	 298
+za	 298
+er	 291
+ia	 290
+ce	 290
+li	 289
+yc	 286
+ych	 285
+ed	 284
+at	 281
+ob	 281
+ak	 280
+_na_	 280
+il	 279
+_,	 279
+_,_	 279
+ok	 277
+sk	 268
+ych_	 265
+_c	 262
+mi	 261
+ol	 260
+me	 260
+l_	 259
+t_	 259
+ku	 258
+ta	 256
+le	 256
+_b	 254
+or	 252
+_a_	 250
+lo	 247
+oc	 246
+vo	 246
+es	 244
+ve	 242
+_vy	 240
+on	 238
+_sa	 231
+as	 231
+da	 230
+aj	 228
+av	 218
+el	 216
+ova	 216
+ic	 215
+ne_	 209
+_do	 208
+sa_	 207
+ka	 205
+_sa_	 204
+te	 203
+j_	 201
+_ro	 199
+P	 198
+_za	 196
+ky	 196
+_S	 195
+je	 194
+ar	 193
+_.	 193
+it	 192
+s_	 192
+em	 191
+ej	 191
+ur	 190
+ad	 189
+_o_	 187
+_._	 187
+ov_	 185
+de	 180
+_%	 179
+om_	 179
+%	 179
+_u	 174
+pre	 173
+dn	 173
+D	 172
+rok	 170
+ie_	 170
+sp	 169
+pri	 167
+_pre	 167
+am	 165
+-	 164
+ke	 164
+eh	 162
+oz	 161
+k_	 160
+ost	 160
+_j	 156
+f	 155
+zn	 153
+g	 152
+kt	 152
+ho_	 151
+eho	 151
+hod	 150
+ku_	 148
+is	 148
+zi	 147
+cn	 147
+eho_	 146
+ej_	 145
+az	 145
+tu	 145
+_pri	 144
+cen	 144
+_st	 143
+ma	 142
+ast	 141
+_ce	 140
+rov	 140
+la_	 138
+ot	 138
+nych	 135
+nyc	 135
+_ob	 133
+z_	 133
+nych_	 131
+N	 130
+li_	 129
+ani	 129
+co	 128
+nt	 128
+ny_	 127
+E	 125
+_ne	 124
+)	 123
+_(	 123
+sti	 123
+A	 123
+(	 123
+cho	 122
+vi	 122
+_sp	 122
+di	 120
+pa	 120
+n_	 119
+ju	 118
+ys	 117
+bo	 117
+_P	 116
+_tr	 115
+V	 114
+je_	 114
+ln	 114
+_i	 113
+ze	 113
+spo	 112
+_N	 112
+nd	 111
+nu	 111
+so	 111
+red	 110
+vn	 110
+kl	 110
+kov	 110
+_cen	 110
+_rok	 109
+tn	 109
+du	 109
+nc	 109
+ap	 109
+d_	 108
+van	 108
+ca	 108
+M	 108
+chod	 107
+ti_	 107
+U	 106
+_ak	 106
+ru	 105
+sta	 105
+ym	 105
+_-	 104
+et	 103
+_h	 102
+est	 102
+_je	 102
+nos	 101
+aci	 101
+us	 100
+dov	 100
+pod	 100
+_to	 100
+tor	 99
+uc	 99
+ras	 98
+ky_	 98
+_s_	 98
+_mi	 97
+*	 97
+uj	 97
+nost	 97
+vys	 97
+ovy	 97
+ez	 97
+oku	 96
+_V	 96
+op	 96
+bc	 96
+rast	 96
+se	 95
+B	 95
+roku	 95
+kto	 94
+ove	 94
+by	 94
+-_	 94
+_ko	 93
+obc	 92
+nie	 91
+ia_	 91
+ka_	 91
+*_	 90
+ali	 90
+lo_	 89
+ovan	 89
+to_	 88
+iz	 88
+_bo	 88
+_l	 88
+odo	 87
+bch	 87
+bchod	 87
+bcho	 87
+sl	 86
+st_	 86
+pred	 86
+C	 86
+pol	 85
+_pred	 85
+R	 85
+ik	 84
+uro	 84
+pi	 84
+ek	 84
+zo	 83
+eni	 83
+obch	 83
+cie	 83
+oku_	 83
+obcho	 83
+ns	 83
+roku_	 82
+ii	 82
+tv	 82
+ba	 82
+ent	 82
+_spo	 81
+tov	 81
+pe	 81
+kon	 80
+kc	 80
+ec	 80
+kci	 80
+ck	 80
+x	 79
+osti	 79
+_Sk	 79
+mi_	 79
+_in	 79
+Sk	 79
+sia	 79
+br	 78
+rh	 78
+val	 78
+olo	 77
+_pod	 77
+%_	 77
+_%_	 77
+bu	 77
+_f	 77
+iv	 77
+_obc	 77
+_obch	 77
+eb	 76
+str	 76
+nej	 76
+_D	 76
+ni_	 75
+ou	 75
+im	 75
+ena	 74
+tre	 74
+_A	 74
+mo	 74
+su	 74
+rz	 73
+_trh	 73
+trh	 73
+_U	 73
+al_	 73
+_ra	 73
+_e	 72
+_C	 72
+sti_	 72
+zv	 72
+te_	 72
+cno	 72
+oj	 72
+ktor	 71
+_roku	 71
+ocn	 71
+ina	 71
+sil	 71
+nov	 71
+alo	 71
+odn	 70
+nan	 70
+oh	 70
diff --git a/libtextcat/data/new_fingerprints/lm/slovenian.lm b/libtextcat/data/new_fingerprints/lm/slovenian.lm
new file mode 100644
index 000000000000..0fb3f18f1659
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/slovenian.lm
@@ -0,0 +1,400 @@
+_	 10406
+a	 2828
+e	 2676
+i	 2458
+o	 2418
+n	 1814
+r	 1484
+v	 1253
+l	 1248
+s	 1228
+t	 1172
+j	 1107
+d	 1085
+k	 911
+p	 880
+a_	 823
+m	 763
+i_	 681
+e_	 678
+_p	 603
+o_	 566
+u	 521
+z	 516
+b	 456
+_s	 435
+je	 434
+,	 416
+,_	 411
+ni	 399
+č	 383
+_v	 372
+_d	 356
+pr	 355
+g	 345
+ra	 336
+_n	 332
+st	 323
+an	 313
+po	 303
+re	 301
+na	 295
+h	 287
+ov	 276
+_pr	 276
+li	 275
+al	 274
+_z	 270
+je_	 259
+la	 255
+š	 253
+ne	 248
+en	 246
+ko	 244
+in	 237
+c	 234
+ti	 234
+v_	 234
+_po	 232
+no	 230
+ve	 230
+_k	 227
+_i	 224
+da	 224
+.	 221
+_j	 221
+ri	 220
+ja	 216
+_t	 214
+se	 213
+ed	 212
+._	 211
+em	 206
+te	 205
+za	 201
+od	 201
+av	 200
+lo	 196
+nj	 194
+_o	 194
+_je	 193
+il	 190
+or	 183
+ka	 181
+sk	 179
+_b	 178
+_je_	 178
+ih	 178
+n_	 177
+_za	 173
+h_	 171
+er	 171
+os	 171
+_na	 168
+va	 168
+ta	 164
+le	 163
+m_	 161
+ev	 157
+ij	 157
+ar	 157
+do	 155
+to	 155
+ž	 154
+A	 153
+el	 150
+_m	 148
+ro	 147
+ol	 146
+_v_	 145
+aj	 145
+di	 143
+N	 142
+S	 142
+at	 140
+ih_	 139
+ki	 138
+de	 137
+_in	 135
+vo	 135
+ga	 134
+me	 131
+in_	 129
+vi	 129
+om	 127
+_in_	 125
+et	 124
+pre	 124
+O	 123
+bi	 120
+I	 119
+da_	 117
+ik	 117
+ma	 115
+E	 114
+so	 113
+bo	 112
+it	 112
+anj	 112
+eg	 110
+ni_	 109
+mi	 108
+ke	 108
+na_	 108
+u_	 108
+lj	 106
+iz	 105
+ob	 105
+_da	 103
+li_	 103
+is	 103
+im	 102
+red	 102
+_pre	 102
+dr	 100
+mo	 99
+P	 99
+_se	 99
+ji	 98
+r_	 97
+ad	 97
+pri	 97
+K	 97
+_l	 97
+tr	 95
+pa	 94
+no_	 94
+j_	 92
+ki_	 91
+ti_	 91
+_pri	 91
+dn	 89
+_P	 88
+ej	 88
+_da_	 87
+ne_	 86
+ega	 86
+_r	 86
+_bi	 86
+l_	 86
+em_	 86
+go	 86
+"	 85
+sl	 85
+ek	 84
+ali	 84
+ove	 84
+ač	 84
+ak	 84
+ci	 83
+ga_	 83
+ko_	 83
+se_	 82
+_S	 82
+jo	 81
+ot	 81
+ja_	 81
+_so	 80
+lov	 80
+L	 80
+D	 79
+V	 79
+as	 78
+_do	 78
+am	 78
+nje	 77
+es	 77
+za_	 77
+_pa	 76
+T	 75
+tu	 75
+_za_	 74
+sti	 74
+_dr	 74
+la_	 74
+_N	 74
+_de	 74
+ega_	 73
+_ko	 73
+og	 73
+ns	 72
+če	 72
+ds	 72
+_bo	 71
+ora	 71
+vn	 71
+ost	 71
+_ne	 71
+ič	 70
+ven	 69
+z_	 69
+či	 69
+_te	 68
+ce	 68
+_se_	 67
+ča	 67
+oč	 67
+M	 66
+_u	 66
+un	 65
+ln	 65
+pos	 64
+ju	 64
+sta	 64
+op	 64
+di_	 63
+ud	 63
+vs	 63
+t_	 62
+nsk	 62
+tv	 62
+on	 62
+ski	 62
+R	 62
+pa_	 62
+_ka	 62
+i,	 61
+so_	 61
+_iz	 60
+_pa_	 60
+s_	 60
+i,_	 60
+pro	 59
+del	 59
+rav	 59
+eni	 59
+oli	 58
+rj	 58
+e,	 57
+še	 57
+ili	 57
+vr	 57
+d_	 57
+_le	 57
+pred	 57
+jo_	 56
+e,_	 56
+nik	 56
+love	 56
+_pred	 56
+ske	 56
+er_	 55
+str	 55
+čn	 54
+pra	 54
+J	 54
+_š	 54
+oven	 53
+_ra	 53
+tn	 53
+_na_	 53
+_so_	 53
+nih	 53
+loven	 53
+si	 52
+ke_	 52
+_g	 52
+ic	 52
+udi	 51
+bi_	 51
+eds	 51
+oj	 51
+ru	 51
+a,	 51
+_pro	 50
+_pos	 50
+nc	 50
+nih_	 50
+ču	 50
+a,_	 50
+_a	 50
+az	 50
+ok	 50
+B	 50
+let	 49
+udi_	 49
+_od	 49
+_K	 49
+aj_	 48
+_bi_	 48
+_ve	 48
+rač	 48
+o,	 47
+_tu	 47
+ija	 47
+ter	 47
+ist	 47
+Z	 47
+reds	 46
+nd	 46
+ali_	 46
+A_	 46
+iti	 46
+bil	 46
+_ob	 46
+o,_	 46
+ati	 46
+tud	 45
+tudi	 45
+_ki	 45
+k_	 45
+be	 45
+aš	 45
+ir	 45
+ža	 45
+do_	 45
+sp	 45
+_ki_	 45
+_st	 45
+ep	 44
+_del	 44
+tudi_	 44
+rž	 44
+aču	 44
+_ni	 44
+ah	 43
+raču	 43
+račun	 43
+iš	 43
+_mo	 43
+avn	 43
+_tud	 43
+čun	 43
+ačun	 43
+_tudi	 43
+_to	 42
+raz	 42
+kr	 42
+ova	 42
+_e	 42
+ogo	 42
+ani	 42
+_"	 42
+ev_	 42
+br	 42
+eb	 42
+sa	 42
+mi_	 42
+tem	 42
+ta_	 41
+prav	 41
+i.	 41
+slov	 41
+ens	 41
+bo_	 41
+že	 41
+_T	 41
+_let	 41
+odo	 41
+slo	 41
+ensk	 40
+ka_	 40
+neg	 40
+ez	 40
+nos	 40
+eč	 40
+_sl	 40
+_V	 40
+rža	 40
+nega	 40
+ili_	 39
diff --git a/libtextcat/data/new_fingerprints/lm/spanish.lm b/libtextcat/data/new_fingerprints/lm/spanish.lm
new file mode 100644
index 000000000000..e40317f956a9
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/spanish.lm
@@ -0,0 +1,400 @@
+_	 25044
+e	 7830
+a	 7437
+o	 5102
+s	 4394
+n	 4358
+i	 4065
+r	 3998
+l	 3634
+d	 3118
+c	 2931
+t	 2834
+u	 2316
+a_	 2269
+e_	 2211
+s_	 1862
+de	 1679
+p	 1673
+_d	 1644
+m	 1447
+_de	 1443
+n_	 1332
+o_	 1301
+en	 1295
+_e	 1216
+es	 1177
+_l	 1132
+de_	 1080
+la	 1060
+os	 1028
+_de_	 1027
+_p	 963
+l_	 910
+ci	 890
+_c	 866
+_a	 866
+os_	 801
+ar	 777
+er	 775
+as	 768
+ra	 746
+nt	 736
+_la	 727
+re	 726
+,_	 724
+,	 724
+el	 722
+ta	 708
+ue	 701
+g	 678
+on	 674
+al	 670
+_s	 666
+co	 653
+b	 637
+an	 622
+v	 616
+la_	 616
+or	 612
+te	 599
+st	 596
+el_	 580
+_la_	 573
+y	 545
+to	 543
+r_	 517
+ad	 512
+ó	 511
+do	 504
+ro	 504
+se	 488
+as_	 488
+q	 487
+qu	 487
+.	 479
+._	 478
+en_	 475
+ca	 460
+in	 459
+un	 456
+_co	 450
+es_	 449
+ic	 449
+_en	 440
+ac	 440
+que	 439
+na	 439
+lo	 430
+_m	 430
+f	 429
+ent	 428
+da	 412
+ue_	 411
+po	 405
+le	 399
+_q	 399
+_qu	 399
+que_	 393
+_que	 388
+ie	 386
+h	 385
+pa	 382
+y_	 371
+ti	 367
+_que_	 365
+_en_	 365
+_y	 361
+tr	 358
+_el	 353
+ri	 349
+ia	 342
+_el_	 333
+_se	 330
+ió	 330
+_y_	 330
+io	 329
+pr	 320
+ón	 317
+ec	 317
+no	 314
+id	 301
+í	 300
+mi	 299
+_t	 299
+ión	 292
+nte	 292
+me	 286
+aci	 283
+do_	 279
+li	 276
+con	 276
+nd	 273
+est	 272
+ni	 272
+á	 271
+di	 270
+_es	 268
+_lo	 267
+ció	 265
+ma	 265
+ón_	 264
+_pr	 263
+_r	 261
+ción	 255
+z	 254
+ra_	 251
+si	 247
+ión_	 246
+oc	 245
+nc	 244
+_u	 244
+_po	 243
+los	 243
+or_	 242
+_con	 241
+is	 239
+del	 238
+_del	 237
+ado	 236
+se_	 233
+_i	 233
+los_	 231
+_re	 231
+por	 229
+_del_	 228
+sta	 228
+del_	 228
+al_	 228
+ne	 226
+_h	 226
+cu	 225
+_n	 225
+_a_	 224
+_v	 224
+_un	 223
+ce	 222
+so	 220
+ción_	 218
+res	 218
+vi	 217
+om	 216
+te_	 212
+_pa	 211
+ien	 210
+j	 209
+E	 208
+_los	 207
+_los_	 207
+to_	 206
+ol	 204
+it	 203
+am	 202
+ació	 201
+rt	 201
+ación	 201
+pe	 197
+ha	 190
+_se_	 189
+nto	 188
+_o	 184
+_E	 184
+on_	 184
+sa	 183
+na_	 182
+ta_	 181
+su	 180
+cia	 180
+mo	 180
+ct	 178
+par	 178
+_f	 177
+_por	 176
+eg	 172
+_in	 172
+ur	 170
+L	 168
+ve	 166
+im	 164
+ga	 163
+_est	 161
+ar_	 161
+ab	 160
+_L	 159
+tu	 158
+at	 158
+no_	 157
+s,	 157
+s,_	 157
+_por_	 156
+por_	 156
+las	 156
+ba	 154
+o,_	 154
+o,	 154
+ento	 151
+et	 150
+C	 150
+_ha	 149
+A	 149
+tra	 148
+ient	 148
+_al	 147
+a,_	 146
+ica	 146
+a,	 146
+pro	 146
+ado_	 145
+ici	 144
+_ca	 144
+an_	 144
+las_	 143
+ara	 143
+nci	 143
+ente	 142
+ú	 142
+rr	 142
+ir	 142
+da_	 141
+em	 141
+ll	 140
+il	 139
+ía	 138
+iv	 138
+_su	 138
+_par	 136
+ul	 136
+ant	 136
+_A	 135
+mp	 135
+_las_	 134
+_las	 134
+_C	 134
+_pro	 133
+men	 132
+P	 132
+des	 131
+com	 130
+ion	 130
+era	 130
+ed	 129
+ida	 129
+sp	 128
+gu	 127
+nte_	 127
+ns	 127
+za	 126
+dos	 125
+M	 125
+cio	 125
+les	 125
+_P	 124
+bl	 124
+_com	 122
+s._	 122
+s.	 122
+_M	 121
+ua	 120
+nta	 120
+mu	 119
+_no	 118
+dad	 118
+ñ	 117
+é	 116
+un_	 116
+va	 116
+ist	 116
+nes	 116
+iento	 115
+one	 114
+ara_	 113
+S	 113
+ada	 113
+_un_	 113
+fi	 111
+pre	 110
+tos	 110
+ter	 109
+ot	 109
+esta	 108
+_me	 107
+ido	 107
+ob	 107
+_g	 105
+br	 105
+go	 105
+ea	 104
+nto_	 104
+ona	 103
+pu	 103
+dos_	 103
+tro	 103
+ier	 103
+para	 102
+ment	 101
+ag	 101
+ero	 101
+gr	 101
+rec	 101
+bi	 101
+ia_	 100
+una	 100
+nic	 99
+ncia	 99
+ía_	 98
+a._	 98
+tos_	 98
+a.	 98
+ran	 98
+lo_	 97
+ones	 97
+rm	 96
+lu	 96
+ron	 95
+con_	 95
+ó_	 95
+nes_	 95
+_ci	 95
+ante	 94
+ch	 94
+_con_	 94
+_para	 94
+ntr	 93
+una_	 93
+para_	 93
+mie	 92
+ico	 92
+fe	 92
+les_	 92
+uc	 92
+ip	 91
+sto	 91
+_ma	 91
+ui	 91
+sta_	 91
+_ve	 90
+cion	 90
+"	 90
+op	 90
+cal	 89
+_mu	 89
+_S	 89
+ro_	 89
+_pe	 88
+ste	 88
+ras	 88
+pl	 88
+_una	 88
+_di	 87
+ento_	 86
+ita	 86
+ione	 85
+ect	 85
+_una_	 85
+mien	 85
+tan	 85
+du	 84
+den	 84
+ndo	 84
+per	 84
+eri	 84
diff --git a/libtextcat/data/new_fingerprints/lm/swahili.lm b/libtextcat/data/new_fingerprints/lm/swahili.lm
new file mode 100644
index 000000000000..56090b40153e
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/swahili.lm
@@ -0,0 +1,400 @@
+_	 16483
+a	 9342
+i	 5293
+a_	 4071
+u	 2730
+k	 2609
+n	 2351
+w	 2076
+m	 1928
+e	 1866
+h	 1800
+o	 1775
+wa	 1743
+l	 1486
+s	 1419
+i_	 1401
+t	 1399
+_k	 1306
+y	 1100
+_w	 969
+li	 945
+wa_	 911
+z	 891
+_wa	 890
+ka	 834
+ku	 799
+r	 770
+b	 733
+an	 727
+ma	 723
+o_	 711
+_m	 707
+na	 698
+ya	 675
+ha	 672
+g	 602
+al	 580
+d	 570
+at	 560
+am	 554
+_n	 549
+_ku	 549
+ik	 543
+_h	 515
+ya_	 514
+A	 494
+is	 487
+_y	 485
+hi	 474
+na_	 471
+_ya	 471
+ta	 468
+sh	 456
+ali	 449
+j	 426
+u_	 423
+ki	 418
+e_	 402
+p	 401
+ti	 401
+_wa_	 399
+f	 392
+_ya_	 390
+ba	 390
+ri	 385
+ng	 385
+il	 380
+c	 358
+hu	 356
+_na	 356
+ni	 355
+za	 354
+zi	 351
+ia	 344
+_na_	 343
+_a	 336
+in	 327
+_ma	 326
+ch	 322
+mb	 317
+ika	 314
+.	 311
+._	 309
+_ka	 307
+as	 306
+ak	 306
+ati	 301
+,	 300
+ka_	 296
+,_	 294
+_u	 292
+kw	 286
+ili	 278
+K	 274
+en	 271
+si	 266
+_kw	 262
+la	 261
+ni_	 261
+ma_	 261
+_s	 258
+kwa	 258
+ar	 256
+ut	 245
+za_	 245
+nd	 242
+mba	 241
+_kwa	 239
+_z	 234
+li_	 233
+un	 233
+ny	 230
+it	 229
+se	 229
+yo	 227
+ia_	 222
+M	 221
+sa	 221
+kat	 217
+_K	 214
+_i	 213
+ika_	 213
+ana	 212
+ish	 212
+kati	 206
+_ha	 204
+on	 201
+ai	 200
+I	 198
+aa	 196
+um	 195
+im	 190
+v	 188
+mu	 187
+amb	 187
+sha	 185
+em	 183
+fa	 181
+zi_	 180
+di	 179
+mi	 178
+_M	 178
+us	 176
+_ki	 176
+ha_	 175
+iw	 172
+ama	 172
+_kat	 168
+_kati	 168
+_hi	 166
+_l	 166
+ra	 166
+kwa_	 165
+la_	 164
+W	 164
+ja	 163
+U	 163
+N	 163
+amba	 161
+ao	 161
+_za	 160
+ji	 160
+B	 157
+iwa	 155
+tik	 155
+wal	 155
+le	 155
+tika	 154
+ge	 153
+lis	 153
+tu	 152
+atika	 152
+to	 152
+atik	 152
+uw	 152
+_kwa_	 151
+A_	 151
+ke	 150
+S	 147
+tika_	 145
+aj	 145
+we	 144
+cha	 144
+bi	 141
+az	 140
+er	 139
+ek	 138
+katik	 138
+ez	 138
+uwa	 137
+kut	 135
+_al	 134
+_B	 134
+ad	 134
+mu_	 133
+_ali	 133
+rik	 132
+_W	 131
+ba_	 131
+kuw	 131
+me	 130
+ali_	 128
+kuwa	 128
+ema	 127
+wan	 127
+bu	 126
+sem	 126
+_A	 125
+ir	 125
+ata	 125
+iz	 124
+_hu	 124
+ay	 124
+ul	 124
+af	 123
+iki	 122
+ema_	 121
+da	 120
+ti_	 120
+sema	 119
+aka	 118
+sema_	 118
+te	 118
+uz	 117
+yo_	 117
+_v	 117
+io	 116
+iy	 115
+uta	 115
+ani	 115
+_wal	 115
+he	 115
+if	 114
+_la	 114
+ab	 114
+go	 112
+_za_	 111
+ama_	 111
+sa_	 111
+pa	 110
+_t	 110
+zo	 110
+nge	 110
+wam	 109
+wali	 108
+ua	 107
+ur	 106
+_c	 106
+ise	 105
+_ch	 105
+isem	 105
+ho	 105
+ye	 104
+iyo	 104
+E	 104
+el	 104
+mo	 103
+ung	 103
+eri	 103
+_wali	 103
+_b	 102
+mba_	 102
+ari	 101
+ita	 101
+isema	 100
+ot	 99
+_la_	 99
+uk	 99
+ao_	 99
+di_	 99
+sha_	 99
+ini	 99
+kuwa_	 98
+uwa_	 98
+ana_	 98
+lise	 98
+lisem	 98
+uli	 97
+shi	 97
+ga	 96
+iwa_	 96
+fu	 96
+T	 96
+R	 95
+_il	 95
+wak	 94
+aw	 94
+isha	 94
+ri_	 93
+_am	 93
+ara	 92
+_cha	 92
+aji	 92
+_ili	 91
+ifa	 91
+O	 90
+_p	 90
+uh	 90
+iri	 90
+chi	 90
+asi	 89
+po	 89
+a.	 89
+ong	 89
+azi	 88
+_j	 88
+_kut	 88
+eny	 88
+nc	 88
+a._	 88
+ko	 87
+uu	 87
+id	 87
+w_	 87
+no	 87
+P	 86
+ah	 86
+ina	 86
+rika	 86
+_Bw	 85
+H	 85
+gu	 85
+uo	 85
+Bw_	 85
+_Bw_	 85
+_se	 85
+Bw	 85
+ib	 84
+_S	 84
+kam	 84
+hi_	 84
+nya	 84
+si_	 83
+a,	 82
+no_	 81
+pi	 81
+ok	 81
+i.	 81
+ip	 81
+kwam	 81
+i._	 81
+amba_	 80
+dh	 80
+end	 80
+ani_	 80
+a,_	 79
+wamb	 79
+kwamb	 79
+_sh	 79
+eza	 79
+nz	 79
+wi	 79
+_kwam	 79
+wamba	 79
+alis	 78
+_kuw	 78
+ngo	 78
+ap	 77
+_N	 77
+any	 77
+ili_	 77
+C	 77
+WA	 76
+vy	 76
+wana	 76
+_hiy	 75
+Wa	 75
+hiyo	 75
+nch	 75
+_hiyo	 75
+de	 75
+_kuwa	 75
+ing	 75
+hiy	 75
+vi	 75
+isha_	 74
+es	 74
+atu	 74
+_Wa	 74
+nchi	 74
+aki	 74
+lim	 73
+da_	 73
+ini_	 73
+ash	 73
+ala	 73
+i,	 73
+ano	 73
+i,_	 72
+_kam	 71
+_wan	 71
+ano_	 71
+mw	 71
+nde	 71
+ji_	 71
+ion	 70
+_amb	 70
+ndi	 70
+_Ka	 70
+eza_	 70
diff --git a/libtextcat/data/new_fingerprints/lm/swedish.lm b/libtextcat/data/new_fingerprints/lm/swedish.lm
new file mode 100644
index 000000000000..1c021242b9fe
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/swedish.lm
@@ -0,0 +1,400 @@
+_	 33494
+e	 8992
+n	 7900
+t	 7859
+a	 7781
+r	 7251
+s	 6435
+i	 5649
+l	 4541
+d	 4079
+o	 3724
+m	 3203
+k	 3058
+g	 2478
+en	 2403
+n_	 2389
+t_	 2073
+de	 1939
+r_	 1910
+v	 1890
+h	 1789
+u	 1782
+_s	 1768
+ä	 1724
+er	 1709
+f	 1597
+en_	 1537
+a_	 1526
+an	 1357
+p	 1320
+et	 1317
+ö	 1278
+å	 1261
+st	 1236
+ar	 1226
+c	 1191
+_d	 1158
+e_	 1116
+in	 1045
+_f	 1027
+te	 1000
+b	 997
+_a	 978
+s_	 974
+ra	 958
+.	 956
+tt	 935
+_i	 898
+_m	 890
+._	 886
+ll	 870
+ta	 844
+_o	 842
+_e	 839
+nd	 820
+ti	 804
+sk	 798
+re	 779
+at	 769
+_de	 754
+om	 743
+m_	 739
+ör	 720
+,	 697
+,_	 695
+ng	 686
+li	 673
+ka	 666
+oc	 662
+_h	 654
+on	 652
+et_	 647
+ch	 645
+ns	 643
+is	 642
+er_	 630
+är	 625
+_v	 614
+_t	 614
+ni	 611
+i_	 609
+_oc	 592
+tt_	 587
+na	 586
+y	 586
+la	 579
+_b	 579
+h_	 577
+kt	 575
+ch_	 568
+ig	 564
+fö	 563
+och	 555
+or	 555
+_och	 554
+och_	 554
+_och_	 553
+me	 548
+den	 548
+om_	 535
+_i_	 531
+d_	 530
+j	 529
+ik	 520
+de_	 520
+för	 518
+ge	 498
+ad	 497
+_k	 491
+_fö	 487
+ri	 484
+el	 482
+il	 481
+so	 480
+al	 474
+g_	 469
+le	 464
+an_	 461
+_för	 447
+si	 437
+ar_	 437
+att	 435
+_p	 434
+es	 420
+ing	 413
+se	 407
+to	 404
+_u	 403
+_en	 403
+and	 398
+den_	 395
+nde	 393
+nn	 393
+_l	 391
+å_	 391
+D	 385
+än	 383
+nt	 382
+l_	 381
+tr	 378
+_D	 372
+va	 370
+am	 369
+sa	 367
+_so	 365
+ga	 364
+_en_	 361
+är_	 358
+ck	 357
+av	 354
+v_	 351
+ed	 347
+ma	 346
+da	 346
+som	 346
+rs	 344
+som_	 344
+ve	 342
+ter	 341
+att_	 341
+ha	 338
+ne	 337
+ut	 335
+as	 332
+ska	 329
+_at	 327
+_att	 326
+_som	 324
+_att_	 324
+_som_	 323
+vi	 322
+ikt	 317
+_av	 316
+det	 316
+_den	 315
+he	 315
+ss	 314
+un	 307
+ke	 304
+_g	 303
+us	 302
+di	 302
+_st	 300
+rn	 297
+_me	 296
+_ä	 295
+ade	 294
+"	 290
+_ha	 290
+av_	 289
+ill	 288
+_n	 286
+_in	 279
+io	 275
+_r	 275
+der	 275
+it	 274
+_av_	 274
+sta	 274
+gen	 272
+isk	 270
+_ti	 269
+id	 265
+na_	 265
+ns_	 264
+ko	 262
+_den_	 261
+ag	 258
+det_	 257
+lig	 257
+era	 256
+ll_	 255
+_det	 252
+_är	 251
+be	 249
+_är_	 248
+ra_	 247
+ion	 244
+-	 241
+pr	 240
+oni	 233
+til	 231
+ten	 228
+_si	 225
+k_	 222
+på	 222
+fr	 221
+ro	 219
+till	 219
+iv	 216
+ls	 216
+ande	 215
+ör_	 214
+_det_	 213
+äl	 212
+_på	 211
+ts	 210
+ens	 209
+med	 209
+mm	 208
+rt	 208
+_till	 208
+_til	 208
+_va	 207
+_fr	 205
+_sk	 205
+var	 205
+nin	 204
+ning	 203
+ol	 201
+ka_	 200
+lle	 198
+ett	 198
+rd	 197
+em	 196
+på_	 195
+x	 195
+rk	 194
+_ut	 194
+ste	 194
+ds	 193
+_vi	 192
+år	 192
+S	 192
+nde_	 191
+are	 191
+ver	 190
+_på_	 190
+nis	 189
+kr	 189
+_med	 188
+all	 188
+ån	 187
+nge	 185
+mo	 184
+os	 183
+ld	 182
+ade_	 181
+_S	 181
+ed_	 180
+rä	 176
+De	 175
+_-	 175
+kan	 174
+ta_	 173
+ng_	 172
+vä	 171
+för_	 170
+ill_	 170
+han	 170
+_De	 170
+pp	 169
+lt	 169
+sam	 168
+nte	 167
+ans	 167
+ton	 166
+ur	 165
+mi	 165
+ess	 165
+kl	 164
+ig_	 164
+ks	 164
+as_	 163
+und	 163
+men	 162
+med_	 161
+_med_	 161
+ak	 161
+Di	 160
+ot	 159
+rna	 159
+ul	 159
+_var	 159
+te_	 158
+gen_	 158
+het	 157
+kto	 157
+str	 156
+_Di	 155
+tad	 155
+lan	 154
+ga_	 154
+iska	 154
+fa	 154
+fi	 154
+så	 154
+Dikt	 153
+Dik	 153
+pe	 153
+ska_	 152
+ja	 152
+H	 151
+res	 151
+ku	 151
+iu	 150
+ande_	 150
+till_	 150
+t.	 150
+ern	 150
+rm	 149
+_Dikt	 149
+_Dik	 149
+ie	 149
+bl	 148
+-_	 147
+od	 147
+_H	 147
+n.	 147
+ist	 147
+_di	 146
+ius	 146
+_"	 145
+la_	 145
+sl	 145
+man	 145
+ren	 145
+_för_	 145
+toni	 144
+kton	 144
+n._	 144
+ktoni	 144
+ikton	 144
+I	 144
+ikto	 144
+nius	 143
+ten_	 143
+onius	 143
+oniu	 143
+toniu	 143
+ing_	 143
+Dikto	 143
+niu	 143
+_ko	 143
+ic	 142
+_sa	 142
+_han	 142
+ett_	 142
+sm	 141
+ba	 141
+M	 141
+gr	 140
+lä	 140
+ex	 138
+t._	 138
+sp	 137
+lla	 137
+_et	 137
+_M	 137
+dr	 137
+rö	 136
+rad	 136
+ek	 136
+_be	 135
+tar	 135
+_-_	 135
+_om	 134
+rl	 134
+E	 134
+mä	 133
diff --git a/libtextcat/data/new_fingerprints/lm/tagalog.lm b/libtextcat/data/new_fingerprints/lm/tagalog.lm
new file mode 100644
index 000000000000..bc87d38d0c92
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/tagalog.lm
@@ -0,0 +1,400 @@
+_	 10664
+a	 6092
+n	 3421
+i	 2332
+g	 2149
+ng	 1488
+an	 1332
+g_	 1308
+ng_	 1243
+t	 1155
+a_	 1138
+o	 1137
+l	 1105
+s	 1067
+k	 1035
+_n	 957
+m	 909
+y	 801
+ang	 787
+u	 767
+ang_	 683
+p	 682
+na	 670
+_a	 634
+la	 596
+.	 572
+in	 561
+r	 559
+sa	 545
+_s	 502
+._	 487
+ma	 476
+ka	 473
+_na	 464
+b	 462
+_m	 458
+al	 448
+d	 445
+pa	 414
+n_	 412
+at	 394
+ak	 393
+h	 378
+ya	 358
+_k	 356
+ag	 350
+ni	 344
+_p	 339
+_sa	 335
+o_	 328
+ta	 308
+_an	 307
+iy	 300
+sa_	 296
+_ang	 294
+_ang_	 293
+t_	 290
+ay	 286
+ga	 283
+on	 280
+it	 275
+_sa_	 265
+ala	 258
+_ng	 256
+am	 252
+_i	 248
+_pa	 248
+i_	 243
+na_	 243
+an_	 240
+e	 239
+_ma	 237
+_ka	 235
+iya	 231
+y_	 229
+il	 228
+li	 228
+w	 226
+_ni	 225
+_na_	 224
+_ng_	 220
+as	 214
+ba	 207
+si	 206
+"	 195
+ti	 195
+ha	 186
+,	 179
+ar	 178
+ing	 173
+ra	 173
+A	 172
+ki	 168
+ong	 167
+_b	 167
+ap	 166
+,_	 162
+ong_	 161
+ko	 159
+ay_	 159
+un	 157
+ul	 155
+yo	 154
+to	 152
+_l	 150
+ah	 148
+is	 147
+hi	 147
+_t	 146
+lan	 145
+ama	 142
+niy	 139
+at_	 138
+_niy	 138
+aka	 136
+wa	 136
+niya	 135
+_niya	 135
+ab	 134
+-	 134
+di	 133
+_si	 132
+"_	 131
+aw	 129
+_d	 126
+_A	 126
+yan	 123
+ya_	 122
+ata	 120
+a.	 120
+gi	 120
+P	 120
+ing_	 118
+um	 115
+o.	 113
+aki	 113
+ri	 113
+ik	 112
+nd	 112
+ila	 111
+mo	 110
+da	 110
+a._	 110
+in_	 109
+la_	 107
+ali	 106
+S	 106
+man	 105
+ig	 105
+iya_	 105
+s_	 104
+_ak	 104
+_at	 103
+_h	 102
+yon	 102
+asa	 101
+ina	 101
+_P	 101
+n.	 99
+N	 98
+aa	 98
+ga_	 97
+_mo	 97
+_ba	 97
+_"	 95
+ito	 94
+bi	 94
+yang	 94
+n._	 93
+pag	 92
+lang	 92
+yang_	 92
+_la	 92
+o._	 90
+K	 90
+_at_	 90
+tu	 88
+_S	 88
+ara	 87
+nga	 87
+ro	 85
+apa	 83
+rr	 82
+lam	 82
+lo	 81
+nan	 81
+_N	 80
+aman	 79
+aha	 78
+mg	 78
+mga	 78
+mga_	 78
+_mga_	 78
+_mg	 78
+_mga	 78
+_K	 78
+siy	 77
+kan	 76
+it_	 76
+san	 76
+d_	 75
+ad	 75
+di_	 74
+tin	 74
+'	 74
+ati	 73
+siya	 73
+kin	 72
+M	 72
+lang_	 71
+mo_	 70
+_mo_	 70
+ako	 70
+uma	 70
+_pag	 69
+pi	 69
+l_	 68
+_siy	 68
+rrr	 68
+_siya	 67
+ula	 67
+_M	 66
+Pa	 66
+iyo	 66
+mi	 66
+bu	 66
+mu	 65
+no	 65
+pu	 65
+nag	 65
+ung	 65
+Na	 65
+ot	 64
+_Na	 64
+niya_	 64
+iyan	 64
+ku	 64
+k_	 63
+go	 62
+awa	 62
+ip	 61
+_Pa	 61
+lu	 61
+_di	 60
+pan	 60
+_ta	 60
+ini	 60
+isa	 60
+nt	 60
+iyang	 60
+_iyo	 59
+_iy	 59
+on_	 59
+tan	 59
+mang	 59
+aba	 59
+gan	 59
+ut	 58
+I	 58
+hin	 58
+nak	 58
+an.	 57
+akin	 57
+_r	 57
+han	 57
+Ka	 57
+_ay	 57
+_ako	 56
+may	 56
+iyon	 56
+rrrr	 55
+Sa	 55
+aga	 55
+to_	 55
+nit	 55
+_ko	 54
+er	 54
+ib	 54
+ari	 54
+ana	 54
+ili	 54
+an._	 54
+ahi	 54
+au	 54
+ala_	 54
+gk	 53
+pa_	 53
+_is	 53
+rin	 53
+ilan	 52
+_kan	 52
+_Ka	 52
+_it	 52
+_Sa	 51
+king	 51
+ko_	 51
+_nak	 51
+gin	 51
+_ay_	 50
+bo	 50
+_iyon	 50
+amang	 50
+'y	 49
+os	 49
+mang_	 49
+_pa_	 49
+kat	 49
+a,	 49
+An	 48
+Ma	 48
+ny	 48
+mag	 48
+_ku	 48
+_ito	 48
+_ha	 47
+yong	 47
+?	 47
+aking	 47
+T	 47
+ni_	 47
+yong_	 47
+_An	 47
+king_	 47
+_akin	 46
+sang	 46
+_nag	 46
+kas	 46
+_aki	 46
+_ni_	 46
+ayo	 45
+kit	 45
+'y_	 45
+mat	 45
+_Ma	 45
+lal	 45
+ot_	 45
+nya	 44
+ban	 44
+ndi	 44
+oo	 44
+_u	 44
+ngi	 44
+_hi	 44
+sang_	 44
+B	 43
+su	 43
+may_	 43
+rrrrr	 43
+p_	 43
+ita	 43
+wal	 43
+ika	 43
+abi	 43
+aan	 43
+_may	 43
+lama	 42
+naka	 42
+mal	 42
+_I	 42
+_ri	 42
+alan	 42
+any	 42
+im	 42
+_pu	 42
+ai	 42
+wala	 41
+anya	 41
+a,_	 41
+_B	 41
+ndi_	 41
+as_	 41
+pat	 41
+po	 41
+nang	 41
+_mag	 41
+laman	 40
+lala	 40
+kal	 40
+g-	 40
+..	 40
+ir	 40
+!	 40
+uk	 40
+gu	 39
+ito_	 39
+ro_	 39
+_g	 39
+_da	 39
+_isa	 39
+_lam	 39
+ilang	 39
+kanya	 39
+w_	 39
+kany	 39
+agk	 38
+pal	 38
+ka_	 38
+_naka	 38
+siya_	 38
+isan	 38
diff --git a/libtextcat/data/new_fingerprints/lm/tamil.lm b/libtextcat/data/new_fingerprints/lm/tamil.lm
new file mode 100644
index 000000000000..8563707d5e9d
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/tamil.lm
@@ -0,0 +1,400 @@
+_	 11468
+Õ	 2697
+Ô	 2533
+´	 1960
+»	 1786
+½	 1249
+Â	 1103
+Ù	 990
+£	 976
+Ø	 849
+¡	 847
+¨	 831
+¿	 821
+À	 794
+¾	 758
+§	 750
+Á	 721
+¹	 715
+¶	 713
+.	 702
+£_	 671
+×	 655
+â	 648
+Æ	 625
+._	 611
+ç	 601
+Å	 571
+¯	 557
+»Õ	 556
+É	 524
+_É	 520
+¢	 518
+_½	 492
+Ç	 489
+_×	 488
+Þ	 484
+_Ç	 482
+¤	 461
+Ä	 442
+¼	 418
+ÿ	 416
+¥	 403
+§_	 398
+½Ô	 373
+_Ø	 368
+ª	 360
+Í	 359
+_Í	 349
+»Ô	 348
+´Õ	 342
+à	 337
+_Â	 331
+õ	 331
+¨_	 323
+_¼	 321
+¡´	 320
+_´	 310
+Õ¿	 308
+Ü	 299
+¢»	 294
+Ó	 292
+´Ô	 292
+ÿ»	 290
+Õ§	 288
+¡Þ	 284
+â_	 279
+ý	 271
+õ´	 266
+ÂÕ	 265
+_»	 265
+¾Ô	 241
+_¾	 234
+´ª	 232
+=	 231
+±	 229
+¤½	 227
+==	 221
+¶Õ	 218
+»_	 218
+Õ§_	 213
+===	 211
+Õ_	 210
+====	 201
+ª_	 199
+´_	 198
+ÀÕ	 197
+=====	 191
+,	 188
+Ø½	 188
+¿Õ	 187
+º	 186
+_¶	 184
+,_	 184
+Ã	 183
+Ô¯	 181
+¿_	 179
+Ô¨	 178
+å	 172
+´ª_	 171
+ì	 169
+ÙÁ	 168
+¢»Õ	 165
+¿Ô	 165
+Ô_	 165
+ç¡	 164
+È	 161
+Þ_	 160
+Í¨	 160
+_Í¨	 157
+«	 156
+_È	 156
+§Á	 152
+Ô´	 152
+Ù»	 151
+Ð	 150
+_Ð	 149
+ä	 149
+ö	 146
+ÕÅ	 146
+Ø½Ô	 145
+¯´	 143
+Ö	 142
+×¶	 142
+ÁÔ	 142
+½Õ	 140
+Á_	 139
+Ô§	 138
+_Éç	 138
+Éç	 138
+¶Ô	 137
+Õ¨	 137
+Æ_	 136
+¢â	 133
+_×¶	 132
+ÔÆ	 128
+¡´Õ	 128
+ÀÔ	 127
+¥¹	 127
+_Ë	 127
+Ë	 127
+_Ø½	 127
+ÕÀ	 125
+öÓ	 125
+ÄÕ	 124
+ÆÔ	 122
+ÅÕ	 121
+Þ£	 120
+Õç	 119
+¼Ô	 119
+×½	 119
+´Ù	 119
+_å	 118
+¯_	 118
+£.	 117
+´ÕÅ	 116
+»Õ¿	 115
+ÂÔ	 115
+_ÂÕ	 113
+â.	 113
+×»	 113
+£._	 112
+¡Þ_	 112
+ÕÙ	 111
+Õ¡	 111
+ÙÄ	 109
+×´	 109
+é	 109
+â._	 108
+_½Ô	 107
+Õ´	 106
+¤_	 105
+ÆÕ	 104
+'	 104
+½¹	 103
+ç_	 102
+¹Ô	 102
+Ø´	 101
+¼Õ	 100
+Éÿ	 100
+_Éÿ	 99
+_×»	 99
+ÔÀ	 98
+Éÿ»	 98
+æ	 98
+_×½	 97
+Å_	 97
+Ô»	 97
+_Éÿ»	 97
+Ô¨_	 97
+¹_	 97
+ß	 96
+±Å	 96
+×´Ô	 96
+»Ô¨	 95
+¡Þ£	 94
+Õ¿_	 94
+Ø»	 94
+ø	 94
+ØÂ	 93
+í	 93
+_Ø½Ô	 93
+¾Õ	 93
+Õ¨_	 92
+ÿ»_	 91
+ÁÕ	 91
+_Éç¡	 90
+Éç¡	 90
+Ðç	 90
+ÕÆ	 90
+_Ðç	 90
+ÿ»Õ	 90
+Ù¹	 89
+_´Ô	 89
+_Ðç_	 88
+_¼Ô	 88
+Ðç_	 88
+ì_	 86
+ç¡´	 86
+ÅÔ	 86
+ÿâ	 85
+¥à	 85
+¯´ª	 84
+¨Æ	 84
+¨ì	 83
+Ô¥	 83
+÷	 83
+_Þ	 83
+´Ä	 82
+à_	 81
+Ô´_	 81
+¨.	 80
+_¾Ô	 80
+¿Õ§	 80
+²	 80
+ÕÁ	 80
+Ä_	 79
+´ÙÄ	 79
+_½¹	 79
+¨Å	 79
+Ô£	 79
+«¶	 78
+¡_	 78
+¨._	 77
+_¶Õ	 77
+§ÁÔ	 77
+_¼Õ	 77
+ë	 77
+Åâ	 76
+Þ£_	 75
+ÔÆ_	 75
+Ù¾	 75
+Â¯	 75
+ÙÂ	 74
+çÿ	 73
+ýà	 72
+è	 72
+¨ì_	 71
+Ô§_	 71
+´ë	 71
+¥Ü	 71
+§Ù	 70
+»Õ§	 70
+§ÙÁ	 70
+£½	 69
+Ù»_	 69
+ªÄ	 69
+ç¡Þ	 69
+Ó_	 68
+Ôõ	 68
+Ø¾	 67
+_Ø´	 67
+Õ¢	 66
+ÄÔ	 66
+»Ô¨_	 66
+à£	 66
+_Ç»	 66
+Ç»	 66
+Ô¹	 66
+Î	 66
+¿Õ§_	 65
+Ôâ	 65
+_»Õ	 64
+¯.	 64
+¹¢	 63
+Õ¥	 63
+Ô¡	 63
+_×´	 63
+_Î	 63
+Ù´	 62
+´ÄÕ	 62
+Õ¿Ô	 62
+¯._	 61
+Éÿ»Õ	 61
+_½Õ	 61
+_×»Ô	 61
+×»Ô	 61
+Ôõ´	 61
+½¥	 60
+ÿ»Õ¿	 60
+_ä	 60
+_Éÿ»Õ	 60
+Ô¾	 60
+Ôç	 59
+×¶Ô	 59
+¡Þ£_	 59
+¤ä	 59
+_ÇÙ	 58
+ÿâ_	 58
+ÙÅ	 58
+ÇÂ	 58
+ÇÙ	 58
+Éÿ»Õ¿	 58
+ºÕ	 58
+»À	 57
+½Ô¯	 57
+¹£	 57
+ýº	 57
+_ÇÂ	 57
+æ£	 56
+ÔÁ	 56
+_×¶Ô	 55
+?	 55
+ý¹	 54
+ÃÕ	 54
+ÙÆ	 54
+»Õç	 54
+_×´Ô	 54
+´ÕÅâ	 53
+»Õ¿_	 53
+_À	 53
+ÕÅâ	 53
+¡´ÕÅ	 53
+ç¡´Õ	 52
+ÇÀ	 52
+ÙÄ_	 52
+×Â	 51
+Ü_	 51
+'_	 51
+_ÇÀ	 51
+ÔÂ	 51
+Í¨ì	 51
+Âç	 51
+î	 51
+â¡	 51
+_Í¨ì	 51
+À_	 51
+Õ¿Õ	 51
+ÙÀ	 51
+_É§	 50
+É§	 50
+½ý	 50
+»Õ§_	 50
+×½Ô	 50
+±ÅÕ	 50
+»¾	 49
+à£_	 49
+Ôà	 49
+õ´ª	 49
+´¥	 49
+»Õ_	 49
+»ÕÀ	 48
+¶Ô§	 48
+ç£	 48
+Õ¡´	 48
+Õ¤	 48
+ÕØ	 48
+À£	 48
+ÀÕ¿	 48
+_Éç¡´	 47
+æ£_	 47
+ê	 47
+Í¨ì_	 47
+×¶Ô§	 47
+Éç¡´	 47
+Â_	 47
+_Í¨ì_	 47
+?_	 46
+Ø¿	 46
+Ô¿	 46
+_Ø»	 46
+¹õ	 46
+_Ù	 46
+õ´ª_	 46
+è£	 45
+´ÙÄ_	 45
+¢Ù»	 45
+¢Ù	 45
+»Ù	 45
+_×½Ô	 44
+½Ü	 44
+Ô£_	 44
+ÕÆÕ	 44
+´Ø	 44
+á	 44
+´£	 44
+½Ôâ	 44
+ÁÔ£	 44
+Á.	 44
+_×¶Ô§	 43
+´ë¡	 43
diff --git a/libtextcat/data/new_fingerprints/lm/thai.lm b/libtextcat/data/new_fingerprints/lm/thai.lm
new file mode 100644
index 000000000000..e4b65ecdad56
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/thai.lm
@@ -0,0 +1,400 @@
+_	 6290
+Ò	 5252
+Ã	 4377
+¹	 3920
+¡	 3050
+è	 2984
+Í	 2657
+§	 2522
+Ñ	 2454
+Á	 2369
+é	 2304
+à	 2158
+Â	 1981
+Ç	 1908
+Õ	 1693
+Å	 1543
+Ô	 1443
+´	 1422
+·	 1398
+µ	 1398
+»	 1301
+Ë	 1245
+Ð	 1239
+¤	 1210
+º	 1181
+Ê	 1081
+¨	 1045
+ä	 978
+ÒÃ	 951
+¾	 907
+ª	 892
+èÒ	 829
+á	 795
+¡Ò	 735
+ã	 722
+¡ÒÃ	 710
+¢	 691
+ÒÂ	 688
+×	 668
+Í§	 595
+.	 588
+ç	 553
+Ø	 543
+ÃÑ	 532
+Õè	 528
+ÃÐ	 522
+»Ã	 522
+·Õ	 477
+Ù	 452
+·Õè	 451
+èÍ	 443
+¹Ò	 441
+Ó	 422
+Ò§	 419
+éÒ	 414
+ì	 388
+¹_	 378
+ÃÃ	 367
+ÒÁ	 360
+°	 354
+Ñº	 349
+Ò_	 347
+éÍ	 345
+»ÃÐ	 340
+Çè	 337
+ÃÒ	 337
+Áè	 336
+ÇèÒ	 336
+à»	 334
+Ò¹	 333
+Ñé	 332
+¡Ã	 328
+´é	 325
+Ö	 322
+_à	 320
+ç¹	 314
+À	 313
+ÁÒ	 299
+Ñ§	 297
+Ò¡	 297
+×Í	 296
+äÁ	 295
+Ñ°	 293
+ÃÑ°	 293
+×è	 290
+â	 289
+äÁè	 288
+¸	 285
+ã¹	 280
+¼	 273
+è§	 268
+¹ÒÂ	 268
+é¹	 266
+¾Ã	 263
+Ñ¹	 263
+³	 263
+áÅ	 256
+¹¡	 254
+ËÒ	 253
+§¡	 252
+×èÍ	 251
+ÁÕ	 251
+ä´	 248
+	 248
+ä´é	 248
+¨Ð	 248
+»ç¹	 247
+à»ç¹	 247
+»ç	 247
+à»ç	 247
+Í¡	 245
+ÇÒ	 245
+ãË	 244
+¶	 244
+ªÒ	 243
+µÔ	 241
+_á	 240
+¡Ñ	 238
+È	 237
+_¡	 236
+µè	 234
+«	 227
+éÇ	 225
+é§	 221
+É	 216
+Â¡	 214
+Ã¤	 213
+ÕÂ	 211
+Ñé§	 211
+ÃÁ	 211
+¢Í	 210
+Ô¹	 209
+èÇ	 206
+Õé	 202
+ÅÐ	 202
+Ë¹	 201
+¹Ñ	 201
+_¹	 200
+µÃ	 197
+Ëé	 196
+§_	 193
+Á¹	 191
+Ðà	 191
+ÀÒ	 188
+ÍÂ	 188
+ÒÇ	 186
+¢Í§	 184
+¹Õ	 184
+ãËé	 183
+¤Ç	 183
+ÃÕ	 181
+§à	 180
+¡Å	 179
+áÅÐ	 178
+èÒ§	 177
+èÒ_	 176
+ÃÃ¤	 176
+_¾	 176
+¤ÇÒÁ	 174
+¹µ	 174
+ÇÒÁ	 174
+¤ÇÒ	 174
+Ñ´	 172
+Ô´	 172
+ÇèÒ_	 171
+¾ÃÃ	 167
+¨Ò	 167
+Í¹	 167
+Òµ	 167
+¹Õé	 167
+¾ÃÃ¤	 166
+¡ç	 166
+¤Ã	 165
+¹à	 165
+è¹	 163
+ºÒ	 162
+¢é	 161
+§ã	 161
+Õ_	 161
+ì_	 154
+ËÅ	 154
+Á×	 154
+éÍ§	 151
+¹¡ÒÃ	 151
+¹¡Ò	 151
+ä»	 150
+Ñ¡	 150
+é_	 148
+ÃÒÂ	 147
+µÑ	 146
+¹·	 146
+ÅÑ	 146
+Â_	 146
+à¾	 145
+Åé	 140
+à¡	 139
+¨Ò¡	 139
+àÁ	 138
+ÃÔ	 138
+¾Å	 137
+Ã×	 136
+·Ñ	 135
+¡Ñº	 134
+ÒÂ¡	 133
+_Ã	 132
+ºÃ	 132
+§ä	 132
+Ãà	 131
+à·	 130
+Åè	 129
+ÒµÔ	 129
+_·	 128
+¡Ô	 128
+µÃÕ	 128
+ÃÑº	 128
+Õ¡	 128
+àË	 127
+¹Í	 127
+µé	 126
+_¹Ò	 126
+ªÒµÔ	 126
+ÅÒ	 126
+ªÒµ	 126
+¹Ç	 126
+Òà	 126
+_áÅ	 125
+§¹	 124
+§¤	 124
+¡ÒÃà	 124
+ÒÃà	 124
+ÍÁ	 123
+Ò¤	 122
+ 	 122
+áµ	 122
+àÊ	 121
+ÇÑ	 121
+Ñé¹	 120
+ÃÃÁ	 120
+Ò·	 119
+¹µÃ	 119
+èÒÇ	 118
+áµè	 118
+§·	 117
+Ç¹	 117
+ÂÑ	 117
+Á¹µÃ	 117
+¹µÃÕ	 117
+Á¹µ	 117
+Á¹µÃÕ	 117
+ÃÍ	 116
+Ùé	 116
+_¹ÒÂ	 116
+àÁ×	 116
+°Á¹	 115
+àÃ	 115
+ÃÑ°Á¹	 115
+ËÁ	 115
+à¢	 115
+Ñ°Á	 115
+Í.	 115
+Ñ°Á¹µ	 115
+ÃÑ°Á	 115
+°Á¹µ	 115
+Ñ°Á¹	 115
+°Á¹µÃ	 115
+°Á	 115
+_áÅÐ	 113
+éà	 113
+Ãè	 113
+èÁ	 112
+ã¨	 112
+_Ê	 112
+¹Ñé	 111
+Ô»	 111
+¹Ñé¹	 111
+èà	 111
+èä	 110
+_Í	 110
+Âà	 110
+_¨	 110
+Ò¨	 109
+»ÃÒ	 108
+¹ÒÂ¡	 108
+_Ë	 107
+Ñ	 107
+éÒ¹	 107
+¨Ñ	 106
+§¡Ò	 106
+_¤	 106
+§¡ÒÃ	 105
+ÇÂ	 105
+Ôµ	 105
+¹é	 105
+ÒÅ	 103
+´Â	 102
+è_	 102
+ÃÐà	 102
+àÍ	 102
+¹¹	 102
+ÍÒ	 101
+â´	 100
+µéÍ	 100
+ªè	 100
+_ä	 99
+ÇÅ	 99
+µéÍ§	 99
+â´Â	 99
+Ã_	 98
+Ðª	 98
+¾Ñ	 98
+»ÃÐà	 98
+Â¡Ã	 97
+Öè§	 97
+¡_	 97
+Öè	 97
+Òª	 97
+é¹_	 96
+ÅÔ	 96
+Ñ°º	 94
+Ò¾	 94
+ÃÑ°º	 94
+¼Ù	 94
+°º	 94
+Âè	 93
+¹ä	 93
+·Ò	 93
+°ºÒ	 92
+ÅèÒ	 92
+Å.	 92
+Ñ°ºÒ	 92
+¡Ñ¹	 92
+Ñ°ºÒÅ	 92
+§Ã	 92
+ÃÑ°ºÒ	 92
+ºÒÅ	 92
+°ºÒÅ	 92
+Ö§	 92
+.Í	 91
+¢éÒ	 91
+Ã¡	 91
+_¾Å	 90
+ÍÂè	 90
+¾Å.	 90
+Íà	 90
+ÍÂèÒ	 90
+ÂèÒ	 90
+¡ÃÐ	 89
+.Í.	 89
+ÂèÒ§	 89
+Õé_	 89
+ÍÂèÒ§	 89
+ÂÑ§	 89
+ÊØ	 89
+µèÍ	 88
+Íº	 88
+_â	 88
+Å.Í	 87
+èÍ§	 87
+ÃÐª	 87
+Áà	 87
+ÂÇ	 87
+ÅÑ§	 87
+¾Å.Í.	 87
+Å.Í.	 87
+¹Õé_	 87
+à´	 87
+Á¡	 87
+¼Ùé	 87
+ÇÔ	 87
+¾Å.Í	 87
+»ÃÐª	 87
+»Ñ	 87
+'	 86
+ÊÔ	 86
+Êè	 86
+Áèä	 86
+_¾Å.	 86
+·Ò§	 86
+ÇÁ	 85
+¡à	 85
+Â§	 85
+._	 85
+¡ÃÑ	 85
+ÍÀ	 85
+ªÇ	 84
+ÒÐ	 84
+¹éÒ	 84
+¡ÃÑ°	 84
+ÀÔ	 84
+·Ó	 84
+ËÒÃ	 84
+_¾Å.Í	 84
+ÍÍ	 83
+§Ê	 83
+ÍÀÔ	 83
+äÁèä	 83
+Ñµ	 82
+»ÃÒÂ	 82
+¤¹	 82
+Í_	 82
diff --git a/libtextcat/data/new_fingerprints/lm/turkish.lm b/libtextcat/data/new_fingerprints/lm/turkish.lm
new file mode 100644
index 000000000000..553be45fd735
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/turkish.lm
@@ -0,0 +1,400 @@
+_	 23226
+i	 8957
+a	 7675
+e	 6219
+n	 5169
+&	 4950
+;	 4950
+l	 4674
+r	 4464
+&i	 3206
+&i;	 3206
+i;	 3206
+s	 3206
+k	 3009
+d	 2977
+t	 2442
+m	 2010
+y	 2001
+u	 1885
+n_	 1725
+g	 1584
+o	 1567
+b	 1470
+e_	 1426
+ü	 1353
+ar	 1273
+la	 1236
+a_	 1209
+i_	 1169
+in	 1124
+_b	 1101
+an	 1097
+er	 1073
+le	 1058
+s;	 1036
+&s;	 1036
+&s	 1036
+;_	 1018
+de	 936
+;n	 918
+&i;n	 917
+i;n	 917
+,_	 872
+_,	 872
+_,_	 872
+,	 872
+i;_	 863
+&i;_	 863
+_k	 816
+en	 769
+r_	 762
+_y	 759
+da	 759
+il	 759
+k_	 750
+z	 739
+nd	 725
+&g;	 708
+g;	 708
+&g	 708
+ra	 697
+_a	 692
+_d	 692
+_s	 676
+'	 673
+_i	 644
+._	 641
+.	 641
+_.	 637
+_._	 637
+c	 637
+ka	 635
+v	 632
+;&	 624
+h	 615
+_g	 597
+ri	 596
+ç	 596
+lar	 583
+li	 580
+ma	 559
+ya	 555
+ler	 553
+p	 547
+re	 529
+al	 529
+ö	 527
+_t	 520
+ir	 508
+ak	 502
+bi	 500
+;l	 480
+in_	 478
+di	 477
+r&	 468
+el	 453
+et	 449
+ek	 445
+n&	 439
+_o	 439
+ol	 437
+da_	 434
+n&i	 433
+n&i;	 433
+ni	 429
+ti	 428
+de_	 425
+an_	 422
+eri	 421
+r&i	 417
+r&i;	 417
+s&	 413
+s&i	 413
+s&i;	 413
+ar&	 412
+me	 407
+te	 405
+a&	 404
+i&	 390
+ay	 387
+ne	 380
+_bi	 373
+_ka	 368
+ar&i;	 367
+ar&i	 367
+u_	 363
+as	 363
+_e	 362
+ta	 359
+&i;l	 352
+i;l	 352
+nda	 350
+ki	 347
+na	 346
+si	 343
+_v	 337
+;&i;	 334
+;&i	 334
+ve	 334
+ara	 333
+en_	 332
+;i	 331
+on	 328
+un	 326
+l&i;	 322
+l&	 322
+l&i	 322
+leri	 322
+ba	 318
+_m	 318
+ik	 315
+mi	 315
+f	 306
+lar&	 302
+lar&i	 302
+sa	 298
+_h	 297
+ld	 296
+&i;&	 290
+i;&	 290
+_ve	 288
+l_	 287
+ge	 286
+is	 285
+ed	 285
+i&s;	 284
+i&s	 284
+;r	 282
+_ya	 279
+_ol	 279
+d&i;	 278
+d&	 278
+d&i	 278
+nl	 277
+kl	 275
+;k	 274
+&i;n_	 271
+;n_	 271
+i;n_	 271
+ile	 270
+or	 269
+iy	 267
+a&s	 264
+a&s;	 264
+y&i;	 262
+ad	 262
+y&	 262
+y&i	 262
+ye	 259
+ha	 258
+es	 258
+t&	 257
+t&i	 257
+t&i;	 257
+ini	 253
+;nd	 253
+i;nd	 253
+ür	 253
+&i;nd	 253
+se	 248
+_ge	 248
+i;nda	 248
+;nda	 248
+;n&i;	 247
+i;n&	 247
+;n&	 247
+&i;n&	 247
+i;n&i	 247
+;n&i	 247
+bu	 245
+_'	 245
+_ba	 244
+as&i	 242
+as&i;	 242
+_de	 242
+as&	 242
+at	 240
+am	 240
+nda_	 239
+ar_	 231
+ve_	 230
+rin	 230
+_ve_	 228
+_bu	 227
+im	 227
+&i;r	 226
+i;r	 226
+ur	 221
+g;&i	 220
+g;&	 220
+&g;&	 220
+yo	 220
+&g;&i	 220
+g;&i;	 220
+ul	 215
+ak_	 215
+ke	 213
+nu	 213
+erin	 211
+g;i	 208
+&g;i	 208
+lan	 207
+bir	 205
+r&i;n	 205
+nde	 202
+rl	 202
+n&i;_	 201
+ko	 201
+ca	 200
+m_	 197
+rd	 196
+t_	 194
+er_	 194
+st	 193
+em	 193
+_sa	 190
+lm	 189
+rt	 188
+_ü	 187
+i;k	 187
+ün	 187
+ola	 187
+&i;k	 187
+lerin	 185
+ce	 185
+'_	 185
+;m	 183
+az	 183
+rk	 182
+yü	 182
+;la	 181
+_bir	 181
+ir_	 180
+n&i;n	 180
+ru	 180
+lu	 180
+;nda_	 178
+e&	 177
+_ç	 176
+_ha	 175
+_ko	 173
+esi	 171
+_ö	 170
+ap	 170
+ni_	 168
+tü	 167
+den	 164
+ind	 161
+di_	 161
+be	 161
+s&i;n	 160
+nin	 159
+üz	 158
+ri_	 155
+y&i;l	 155
+_p	 154
+nin_	 153
+&s;_	 152
+_y&	 152
+edi	 152
+s;_	 152
+_y&i;	 152
+_y&i	 152
+yl	 151
+le_	 151
+inde	 150
+eti	 150
+ala	 150
+&i;&s	 149
+ele	 149
+i;&s;	 149
+;&s;	 149
+;&s	 149
+i;&s	 149
+ek_	 148
+ere	 148
+çi	 147
+du	 145
+ön	 145
+z_	 144
+na_	 144
+eri_	 143
+ec	 142
+gö	 142
+i;&g;	 141
+s&i;_	 141
+bir_	 141
+&i;&g	 141
+i;&g	 141
+ah	 141
+;&g;	 141
+;&g	 141
+_gö	 140
+lar_	 140
+eli	 140
+a&g;	 140
+a&g	 140
+dan	 140
+ac	 140
+iç	 140
+an&	 140
+u&	 139
+;&g;&	 138
+_yü	 138
+an&i	 138
+an&i;	 138
+pa	 138
+it	 137
+_ola	 137
+_bir_	 136
+;t	 135
+ör	 135
+ne_	 135
+ini_	 134
+lma	 134
+kan	 133
+ab	 132
+to	 131
+ba&	 131
+kar	 130
+r&i;_	 130
+_ar	 129
+ili	 129
+li_	 129
+ki_	 128
+bu_	 127
+anl	 127
+dü	 127
+ler_	 126
+_ba&	 126
+kon	 126
+ll	 125
+tl	 125
+ine	 125
+e&g;	 124
+e&g	 124
+_il	 124
+_bu_	 124
+re_	 124
+bil	 123
+&s;i	 123
+;&i;n	 123
+s;i	 123
+ede	 123
+zd	 123
+''	 122
+_da	 122
+_''	 122
+_tü	 122
+ret	 122
+_-_	 121
+_''_	 121
+mas	 121
+''_	 121
+-	 121
+dan_	 121
+leri_	 121
+;u	 121
+_-	 121
+ev	 121
diff --git a/libtextcat/data/new_fingerprints/lm/ukrainian.lm b/libtextcat/data/new_fingerprints/lm/ukrainian.lm
new file mode 100644
index 000000000000..438bbdabae46
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/ukrainian.lm
@@ -0,0 +1,400 @@
+_
+о
+и
+а
+╕
+в
+н
+р
+т
+е
+д
+л
+к
+у
+п
+с
+_п
+м
+и_
+я
+_в
+з
+╕_
+а_
+б
+о_
+е_
+ь
+г
+ч
+_т
+ов
+_з
+_д
+у_
+в╕
+.
+_с
+ли
+ро
+в_
+на
+по
+ш
+ю
+ти
+й
+ж
+ор
+х
+_к
+ит
+ин
+щ
+╕д
+"
+_б
+я_
+до
+ви
+ц
+О
+ом
+ко
+_н
+пр
+╓
+ра
+ни
+С
+._
+то
+од
+ка
+ло
+_по
+ри
+м_
+ю_
+ки
+_пр
+ал
+А
+н╕
+ть
+_м
+ен
+ол
+ер
+,
+го
+ь_
+ою
+"_
+_до
+ар
+за
+й_
+на_
+_в_
+во
+ил
+бу
+та
+╖
+_щ
+ав
+ки_
+_╕
+що
+И
+об
+да
+уд
+д╕
+мо
+_бу
+_╕_
+ть_
+Т
+ог
+Р
+_за
+,_
+╕в
+_ц
+Н
+╕н
+ою_
+╕л
+ст
+п╕
+де
+ат
+ос
+те
+ну
+не
+_що
+_в╕
+в╕д
+_о
+дн
+ти_
+ла
+а╓
+ли_
+ого
+т╕
+он
+П
+о╖
+хо
+ик
+_ч
+ле
+_р
+╖_
+л╕
+ц╕
+_П
+ом_
+що_
+но
+р╕
+ду
+ить
+_п╕
+ьк
+н╕_
+_"
+же
+з_
+_не
+ся
+аж
+Я
+З
+В
+_г
+╓_
+х_
+_ви
+ис
+_то
+оро
+ва
+нн
+_л
+ов╕
+_що_
+ди
+про
+_мо
+ль
+му
+ем
+н_
+ий_
+_т╕
+ати
+Я_
+ще
+_про
+К
+оди
+оло
+рт
+ак
+ить_
+ад
+о╖_
+ив
+ля
+ий
+_я
+_Н
+го_
+до_
+_З
+_ка
+п╕д
+ня
+_ко
+_на
+че
+чи
+_со
+_ст
+а╓_
+_з_
+же_
+при
+ся_
+ови
+б╕
+ка_
+╕й
+ого_
+пе
+би
+╕ль
+╕т
+к_
+_буд
+ма
+со
+си
+буд
+св
+пов
+оз
+ок
+Л
+_при
+Г
+Д
+оч
+тор
+ур
+га
+уде
+аз
+ел
+ан
+их_
+╕льк
+ити
+ен╕
+к╕
+ому
+их
+ен╕_
+льк
+_до_
+_х
+ве
+ОС
+му_
+_п╕д
+не_
+ння
+зн
+буде
+ча
+ому_
+али
+╕я
+ц╕_
+ин_
+_буде
+╕р
+╕с
+ння_
+д_
+!
+чен
+ф
+Й
+ов╕д
+_пра
+дов
+льки
+ув
+ру
+ре
+гр
+_пер
+_не_
+╕да
+тер
+рон
+Й_
+енн
+рн
+пер
+им
+ши
+╕льки
+ла_
+льки_
+шо
+ба
+_й
+."
+в╕р
+_т╕ль
+ход
+ьки
+_соб
+иш
+дем
+сто
+_С
+_К
+ви_
+арти
+_сто
+_В
+СТ
+вя
+нк
+вч
+вс
+дно
+_л╕
+т╕л
+!_
+_ки
+_у
+╕й_
+ван
+ьки_
+ня_
+т╕ль
+чо
+рти
+бит
+ення
+ину
+_св
+вин
+д╕_
+пра
+ну_
+каж
+_па
+_пе
+_за_
+удем
+будем
+т╕льк
+арт
+кою
+ьо
+па
+I
+зна
+але
+щен
+."_
+аже
+пов╕
+за_
+_ро
+_гр
+ми
+_т╕л
+соб
+РО
+_в╕д
+карт
+каже
+*
+ЗА
+Ч
+_стор
+╕нк
+ож
+Б
diff --git a/libtextcat/data/new_fingerprints/lm/vietnamese.lm b/libtextcat/data/new_fingerprints/lm/vietnamese.lm
new file mode 100644
index 000000000000..14221268dc1e
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/vietnamese.lm
@@ -0,0 +1,400 @@
+_	 88044
+n	 17000
+h	 12823
+t	 9071
+i	 8490
+c	 8394
+g	 8035
+ng	 6718
+_t	 6352
+_c	 5234
+a	 5083
+g_	 4883
+ng_	 4882
+_n	 4379
+n_	 4365
+i_	 4365
+u	 4149
+m	 3648
+à	 3635
+nh	 3480
+o	 3451
+Ç	 3193
+_Ç	 3168
+r	 3011
+l	 2692
+Ü	 2659
+,	 2328
+,_	 2295
+c_	 2279
+_l	 2263
+ch	 2226
+v	 2161
+th	 2158
+a_	 2132
+_th	 2113
+y	 2111
+.	 2107
+t_	 2106
+h_	 2074
+_v	 2057
+_h	 1888
+_m	 1834
+_ch	 1813
+s	 1749
+nh_	 1715
+u_	 1679
+á	 1668
+à_	 1649
+tr	 1611
+b	 1589
+_tr	 1581
+_nh	 1541
+_b	 1530
+m_	 1505
+p	 1483
+._	 1455
+k	 1429
+_s	 1415
+o_	 1380
+y_	 1371
+_k	 1367
+_ng	 1348
+©	 1343
+e	 1296
+ó	 1208
+	 1199
+ô	 1181
+¶	 1139
+å	 1132
+T	 1126
+hi	 1121
+â	 1081
+ì	 1058
+ê	 1055
+d	 1040
+_g	 1039
+kh	 1034
+_kh	 1027
+_T	 994
+©i	 967
+là	 943
+_là	 941
+"	 926
+ä	 916
+Ü©	 901
+an	 893
+_d	 888
+Ó	 877
+©i_	 859
+on	 853
+Ã	 848
+N	 846
+	 820
+ó_	 813
+	 801
+ôn	 795
+ph	 776
+_p	 772
+_ph	 752
+û	 752
+§	 734
+hÜ	 728
+ho	 715
+và	 709
+_và	 703
+gÜ	 702
+®	 700
+_r	 696
+H	 693
+_là_	 691
+là_	 691
+Ü©i	 684
+àn	 679
+ên	 677
+ông	 676
+ha	 672
+gi	 663
+C	 656
+_gi	 655
+Ö	 654
+gÜ©i	 646
+gÜ©	 646
+Ü©i_	 624
+ông_	 610
+ngÜ	 610
+_ngÜ	 608
+ác	 606
+ú	 601
+ngÜ©	 600
+ngÜ©i	 600
+_ngÜ©	 598
+gÜ©i_	 594
+ûa	 587
+cû	 586
+_cû	 585
+¶t	 585
+cûa	 585
+ên_	 585
+_cûa	 584
+có	 583
+ûa_	 582
+_có	 581
+cûa_	 581
+ã	 581
+_cûa_	 580
+¶t_	 578
+_N	 574
+có_	 574
+»	 573
+_có_	 572
+i	 568
+À	 562
+	 562
+m¶	 557
+_C	 553
+_m¶	 551
+p_	 540
+Æ	 540
+m¶t	 538
+m¶t_	 534
+_m¶t	 532
+ìn	 528
+_m¶t_	 528
+ti	 526
+i	 525
+Ù	 517
+Î	 512
+ình	 500
+..	 500
+	 497
+và_	 497
+_và_	 496
+æ	 491
+q	 490
+qu	 490
+_H	 487
+_q	 484
+_qu	 484
+ong	 481
+ong_	 471
+há	 471
+x	 470
+hô	 468
+¿	 466
+_"	 460
+Ü®	 456
+ro	 453
+ình_	 445
+ì_	 434
+_x	 434
+ã_	 427
+í	 423
+_ti	 423
+in	 422
+ân	 421
+"_	 418
+i	 415
+Ön	 413
+ron	 412
+V	 411
+rong	 410
+§i	 410
+rong_	 409
+ác_	 405
+ª	 400
+n	 399
+hôn	 398
+åi	 395
+ay	 390
+_V	 387
+h»	 382
+hà	 380
+ày	 377
+Ãt	 376
+uy	 374
+ÇÜ	 374
+_ÇÜ	 373
+§i_	 372
+cá	 371
+_cá	 367
+nà	 366
+_	 366
+hú	 366
+_nà	 365
+ra	 363
+hông	 362
+ho_	 359
+ân_	 356
+án	 356
+°	 355
+åi_	 354
+ai	 352
+hu	 352
+cho	 352
+Ü®c	 351
+®c	 351
+Ón	 351
+_cho	 349
+tro	 347
+t	 347
+ào	 347
+_tro	 346
+_tron	 346
+ñ	 346
+tron	 346
+trong	 346
+M	 345
+khô	 340
+âu	 338
+_khô	 338
+cho_	 337
+_cho_	 336
+hông_	 336
+ay_	 333
+ch_	 332
+Çã	 331
+Ãt_	 331
+(	 331
+_(	 330
+Ò	 329
+_Çã	 329
+ÇÜ®	 328
+_ÇÜ®c	 328
+)	 328
+ÇÜ®c	 328
+_ÇÜ®	 328
+khôn	 324
+_ñ	 324
+_khôn	 322
+Çã_	 322
+_Çã_	 320
+ò	 318
+ån	 318
+không	 316
+ào_	 316
+Ü®c_	 316
+®c_	 316
+nhÜ	 315
+Ü_	 315
+»ng	 313
+»ng_	 313
+»n	 313
+_nhÜ	 313
+Th	 312
+hì	 311
+Û	 310
+h»n	 310
+h»ng_	 310
+h»ng	 310
+iê	 309
+gh	 309
+u	 307
+ta	 307
+anh	 307
+¡	 307
+ai_	 306
+àng	 306
+ày_	 304
+ÇÜ®c_	 298
+ÜÖ	 295
+S	 295
+:	 294
+t_	 294
+e_	 294
+:_	 290
+Î_	 289
+ua	 288
+æn	 288
+ài	 286
+u_	 285
+_nh»	 285
+nh»	 285
+nh»ng	 285
+nh»n	 285
+_nh»n	 285
+_Th	 285
+n_	 284
+n	 283
+Ø	 281
+_M	 281
+A	 281
+úc	 278
+L	 277
+ø	 277
+ÜÖn	 276
+_ha	 276
+n,	 275
+Öng	 275
+ÜÖng	 275
+an_	 272
+ài_	 271
+iu	 269
+sÓ	 269
+n,_	 268
+¿_	 268
+on_	 267
+_sÓ	 267
+các	 265
+àng_	 265
+_các	 264
+anh_	 264
+ngh	 264
+_ta	 263
+hi_	 262
+hàn	 261
+_	 261
+âu_	 261
+Àn	 260
+ù	 260
+_ngh	 257
+ia	 255
+¢	 252
+...	 252
+êu	 251
+Ùc	 251
+i,	 249
+iu_	 248
+nhi	 247
+B	 246
+i,_	 245
+Óng	 244
+ª_	 244
+co	 244
+_nhi	 244
+¥	 244
+Ü§	 244
+iên	 243
+D	 243
+Tr	 241
+_S	 240
+hÜ_	 239
+òn	 237
+hÃ	 236
+hÆ	 233
+K	 233
+Öng_	 232
+ôi	 232
+ÜÖng_	 232
+Àn_	 231
+_co	 231
+n_	 229
+hå	 229
+äi	 229
+yê	 229
+Ûn	 229
+¢n	 228
+Ûng	 228
+_L	 227
+Ûng_	 226
+inh	 226
+Çi	 225
+mà	 225
+_Çi	 225
+ng,	 224
+ang	 224
+P	 224
+n	 224
+g,	 224
+g,_	 223
+_v§	 223
diff --git a/libtextcat/data/new_fingerprints/lm/welsh.lm b/libtextcat/data/new_fingerprints/lm/welsh.lm
new file mode 100644
index 000000000000..c25d4a410bef
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/welsh.lm
@@ -0,0 +1,400 @@
+_	 78614
+a	 18113
+d	 17890
+y	 16837
+e	 14108
+n	 13902
+r	 13869
+i	 12928
+o	 9972
+l	 9188
+h	 7454
+g	 7165
+w	 7010
+t	 6296
+f	 6080
+u	 5400
+n_	 5159
+_y	 5051
+dd	 4946
+s	 4884
+r_	 4547
+m	 4364
+d_	 4223
+yn	 4082
+_a	 4020
+c	 3707
+th	 3301
+u_	 2900
+yd	 2900
+ae	 2649
+l_	 2588
+_g	 2547
+.	 2460
+'	 2458
+._	 2408
+wy	 2334
+yn_	 2331
+_d	 2307
+b	 2267
+ym	 2262
+ra	 2261
+an	 2235
+ar	 2228
+ol	 2218
+ia	 2212
+i_	 2199
+ed	 2191
+_yn	 2038
+_i	 2020
+y_	 1983
+_c	 1934
+_yn_	 1861
+ei	 1815
+it	 1796
+g_	 1787
+ith	 1779
+dd_	 1745
+h_	 1741
+ydd	 1731
+ai	 1709
+au	 1708
+'r_	 1655
+'r	 1655
+_y_	 1621
+di	 1615
+,	 1613
+,_	 1608
+da	 1585
+od	 1546
+_o	 1535
+ad	 1532
+th_	 1510
+ll	 1494
+au_	 1492
+_s	 1415
+er	 1359
+o_	 1350
+io	 1311
+a_	 1299
+ol_	 1294
+_e	 1273
+_h	 1249
+cy	 1246
+yr	 1243
+en	 1228
+p	 1217
+_f	 1212
+_cy	 1203
+mr	 1200
+gy	 1193
+ymr	 1185
+ha	 1172
+hy	 1164
+eg	 1159
+do	 1151
+edd	 1147
+G	 1134
+we	 1107
+C	 1089
+_ar	 1078
+_m	 1075
+yf	 1057
+de	 1048
+fe	 1047
+_G	 1045
+ch	 1043
+rae	 1023
+el	 1016
+no	 1010
+ni	 1010
+_b	 1009
+ne	 1001
+ef	 992
+ri	 983
+et	 978
+_C	 957
+_gy	 952
+_a_	 943
+eth	 943
+_.	 940
+_._	 939
+eit	 930
+eith	 927
+ys	 921
+wyd	 912
+ga	 901
+_i_	 893
+s_	 887
+mrae	 878
+mraeg	 878
+raeg	 878
+ymrae	 878
+aeg	 878
+ymra	 878
+mra	 878
+_p	 856
+aet	 850
+aeth	 850
+_n	 844
+un	 838
+on	 836
+ait	 833
+aith	 833
+nn	 830
+at	 827
+oe	 823
+li	 805
+_r	 801
+ddi	 795
+gw	 789
+ma	 783
+le	 777
+nt	 772
+ho	 769
+ff	 766
+yr_	 764
+na	 753
+la	 748
+rh	 747
+eg_	 734
+si	 733
+ng	 732
+dol	 732
+ro	 718
+al	 712
+_dd	 706
+wn	 705
+oed	 705
+Gy	 704
+dy	 701
+Cy	 696
+o'	 692
+ar_	 691
+ny	 690
+Gym	 678
+wr	 677
+id	 676
+_Gy	 672
+_o_	 668
+Gymr	 667
+if	 662
+ith_	 662
+_ar_	 660
+iad	 657
+_w	 657
+fo	 656
+eu	 655
+aeg_	 650
+raeg_	 650
+aith_	 648
+or	 648
+_Gym	 646
+fa	 642
+re	 638
+_Cy	 638
+_Gymr	 635
+_gw	 633
+fy	 633
+oedd	 633
+edd_	 629
+rd	 627
+od_	 622
+ac	 619
+ddo	 612
+an_	 607
+Gymra	 606
+er_	 605
+A	 604
+eth_	 601
+hw	 596
+ydd_	 591
+o'r	 586
+o'r_	 586
+es	 583
+ir	 579
+dw	 573
+go	 559
+yl	 548
+rw	 545
+aeth_	 545
+wydd	 543
+aw	 539
+_rh	 539
+dr	 537
+ly	 537
+fn	 534
+dau	 533
+_hy	 531
+t_	 531
+sg	 529
+'n	 529
+*	 528
+'n_	 523
+_*	 522
+nyd	 521
+nydd	 521
+M	 519
+st	 518
+Y	 516
+sy	 515
+yd_	 513
+lw	 512
+_ga	 508
+iai	 503
+il	 502
+_l	 499
+rt	 494
+ad_	 493
+_yr	 493
+_yr_	 492
+as	 492
+dol_	 492
+f_	 491
+dda	 491
+ig	 490
+og	 484
+wa	 479
+he	 478
+iaith	 477
+iait	 477
+oedd_	 475
+_ma	 473
+c_	 472
+Cym	 470
+te	 469
+_ym	 467
+am	 467
+_M	 465
+_ia	 462
+efn	 462
+i'	 460
+ie	 458
+_Cym	 458
+_ac	 457
+dau_	 456
+yw	 455
+ew	 453
+fr	 441
+fod	 441
+_A	 441
+du	 437
+_sy	 434
+e_	 432
+wi	 426
+Cymr	 426
+se	 425
+B	 424
+D	 424
+_Cymr	 423
+bl	 423
+lu	 420
+in	 417
+_t	 417
+tr	 414
+ac_	 413
+wed	 410
+os	 410
+_iai	 407
+_iait	 407
+el_	 405
+_ac_	 405
+rha	 404
+m_	 404
+is	 403
+on_	 401
+eu_	 393
+hi	 393
+rdd	 393
+id_	 389
+_Y	 388
+ry	 387
+odd	 387
+rwy	 387
+rf	 386
+io_	 380
+ynn	 380
+cyf	 380
+hr	 380
+_cyf	 379
+yddi	 379
+cyn	 372
+_de	 372
+rth	 371
+ru	 368
+S	 363
+wei	 363
+ysg	 362
+_B	 362
+u'	 361
+yddo	 360
+wn_	 360
+so	 359
+dio	 359
+_ei	 358
+N	 356
+dwy	 355
+_da	 353
+me	 353
+gan	 353
+gyf	 353
+w_	 352
+_o'	 351
+fer	 349
+nol	 347
+hyn	 346
+ddy	 346
+af	 346
+ta	 343
+ddol	 343
+_fe	 340
+nd	 340
+mae	 338
+_cyn	 338
+efnyd	 337
+fnydd	 337
+fny	 337
+efny	 337
+fnyd	 337
+iad_	 335
+_mae	 333
+ion	 333
+_ll	 330
+def	 330
+_gyf	 327
+nt_	 326
+i'r_	 326
+-	 326
+i'r	 326
+weith	 325
+weit	 325
+defn	 325
+defny	 325
+bo	 324
+hyd	 323
+by	 322
+_si	 321
+ir_	 321
+hau	 318
+nod	 318
+edi	 315
+I	 314
+fyd	 313
+wyr	 313
+ada	 311
+ddio	 310
+rif	 309
+sia	 307
+sa	 306
+fel	 305
+tha	 305
+_S	 302
+_ne	 302
+_u	 301
+fod_	 300
+_o'r	 300
+yg	 300
+_o'r_	 300
+_i'	 299
+ge	 299
+dia	 299
diff --git a/libtextcat/data/new_fingerprints/lm/yiddish_utf.lm b/libtextcat/data/new_fingerprints/lm/yiddish_utf.lm
new file mode 100644
index 000000000000..e3386a3c1d86
--- /dev/null
+++ b/libtextcat/data/new_fingerprints/lm/yiddish_utf.lm
@@ -0,0 +1,400 @@
+�	 29767
+_	 13552
+_�	 6516
+�	 4273
+�	 3670
+א	 3670
+ע	 3261
+�	 3261
+��	 2826
+ע�	 2826
+א�	 2785
+��	 2785
+י	 2565
+�	 2565
+�	 2082
+ר	 2082
+��	 2062
+י�	 2062
+�	 1857
+ט	 1857
+�	 1828
+ַ	 1828
+�	 1793
+ן	 1793
+_א	 1537
+�_	 1532
+ן_	 1532
+��	 1527
+ַ�	 1527
+אַ	 1517
+�ַ	 1517
+ר�	 1355
+��	 1355
+�	 1270
+ל	 1270
+�	 1268
+אָ	 1268
+ָ	 1268
+�ָ	 1268
+�ַ�	 1240
+אַ�	 1240
+נ	 1232
+�	 1232
+אָ�	 1229
+�ָ�	 1229
+��	 1229
+ָ�	 1229
+נ�	 1181
+��	 1181
+ו	 1116
+�	 1116
+�	 1031
+ד	 1031
+ט�	 1012
+��	 1012
+ל�	 1007
+��	 1007
+ו�	 975
+��	 975
+ד�	 965
+��	 965
+פ�	 929
+�	 929
+פ	 929
+��	 929
+�ר	 873
+ער	 873
+א�	 870
+��	 870
+ז	 868
+�	 868
+�	 832
+ס	 832
+�	 797
+ק	 797
+_א�	 784
+מ	 766
+�	 766
+_א�	 752
+��	 747
+מ�	 747
+�	 742
+ג	 742
+�	 725
+ש	 725
+ט_	 699
+�_	 699
+װ	 691
+�	 691
+װ�	 674
+��	 674
+�	 667
+ײ	 667
+��	 664
+ג�	 664
+�	 661
+ֿ	 661
+ק�	 654
+��	 654
+��	 652
+ֿ�	 652
+ש�	 651
+��	 651
+��	 643
+ז�	 643
+פֿ	 641
+�ֿ	 641
+פֿ�	 638
+�ֿ�	 638
+_אַ	 638
+ר_	 592
+�_	 592
+_ד	 560
+_ד�	 554
+,	 551
+,_	 534
+ב	 517
+�	 517
+_פ�	 502
+_פ	 502
+ב�	 472
+��	 472
+ס�	 436
+��	 436
+צ	 436
+�	 436
+צ�	 433
+��	 433
+_װ	 430
+_װ�	 429
+�	 410
+ה	 410
+�ר_	 404
+_פֿ	 404
+ער_	 404
+_מ	 400
+_מ�	 396
+גע	 390
+�ע	 390
+_ז	 390
+_ז�	 386
+�ע�	 384
+ען	 384
+גע�	 384
+�ן	 384
+ער�	 382
+�ר�	 382
+.	 374
+אי	 372
+�י	 372
+ּ	 366
+�	 366
+��	 363
+ה�	 363
+�י�	 362
+אי�	 362
+_ג	 359
+ױ	 357
+�	 357
+_ג�	 356
+ון	 349
+�ן	 349
+י_	 346
+�_	 346
+ע_	 343
+�_	 343
+�ן_	 337
+ון_	 337
+�ע	 334
+דע	 334
+_אי	 331
+ך	 330
+�	 330
+�ע�	 323
+��	 323
+דע�	 323
+ּ�	 323
+��	 322
+ײ�	 322
+ען_	 321
+�ן_	 321
+��	 320
+ױ�	 320
+�י	 317
+די	 317
+�ַ	 311
+�ַר	 311
+ײ�	 311
+�ר	 311
+ַר	 311
+ײַ	 311
+��	 311
+לע	 310
+�ע	 310
+._	 307
+-	 305
+�_	 297
+ַ_	 297
+�	 294
+כ	 294
+�ע	 290
+נע	 290
+ס_	 289
+�_	 289
+פּ	 288
+�ּ	 288
+ײַ�	 287
+�ַ�	 287
+ך_	 283
+�_	 283
+�ַ_	 274
+אַ_	 274
+ַר�	 272
+�ר�	 272
+לע�	 261
+�ע�	 261
+_ה�	 260
+_ה	 260
+_צ	 259
+�ש	 257
+יש	 257
+_צ�	 256
+זי	 254
+�י	 254
+פּ�	 252
+�ּ�	 252
+מע	 248
+�ע	 248
+_ק	 247
+נע�	 247
+�ע�	 247
+טע	 245
+�ע	 245
+_ק�	 245
+או	 244
+�ו�	 244
+�ו	 244
+או�	 244
+�ל	 238
+על	 238
+�א	 235
+הא	 235
+הא�	 235
+שט	 235
+�ט	 235
+�א�	 235
+כ�	 234
+��	 234
+_ב�	 231
+�ער	 231
+_ב	 231
+ַנ	 229
+�נ	 229
+�נ�	 228
+ַנ�	 228
+_או	 227
+_גע	 226
+�	 219
+ם	 219
+"	 218
+�ע�	 217
+מע�	 217
+�ע	 217
+װע	 217
+�ל	 216
+ַל	 216
+_זי	 215
+_נ	 215
+על�	 212
+�ל�	 212
+�א	 211
+רא	 211
+_נ�	 211
+טע�	 211
+�ע�	 211
+װא	 210
+�א	 210
+_דע	 210
+�א�	 209
+װע�	 209
+װא�	 209
+�ע�	 209
+�ש�	 208
+יש�	 208
+�ק	 207
+יק	 207
+רא�	 206
+�א�	 206
+�_	 205
+ז_	 205
+�י	 196
+מי	 196
+_ש	 195
+מי�	 195
+�י�	 195
+�ַל	 193
+_ש�	 191
+ֿא	 189
+�א	 189
+�ֿא	 189
+ֿא�	 188
+�ו	 188
+ֿו�	 188
+ֿו	 188
+�ו�	 188
+�א�	 188
+�ון	 187
+�אָ	 186
+_הא	 185
+�ֿו	 184
+_ע	 179
+_די	 178
+�א	 176
+טא	 176
+טא�	 175
+�א�	 175
+ָס	 174
+�ָס	 174
+יט	 174
+�ט	 174
+�ס	 174
+ל_	 173
+�_	 173
+�י_	 173
+די_	 173
+ם_	 171
+�ל�	 171
+�_	 171
+ַל�	 171
+_ע�	 171
+�ָט	 169
+�ט	 169
+ָט	 169
+יך	 168
+�ך	 168
+�ָר	 166
+�י�	 166
+ָר	 166
+�ר	 166
+זי�	 166
+ני	 164
+ענ	 164
+�י	 164
+�נ	 164
+�י	 163
+רי	 163
+יך_	 163
+�ך_	 163
+�אָ	 162
+ענ�	 162
+�נ�	 162
+�אַ	 160
+�ט	 160
+עט	 160
+_י	 158
+�י�	 157
+�ר	 157
+רי�	 157
+יר	 157
+-�	 156
+ָס_	 155
+�ס_	 155
+�י	 154
+_מי	 154
+לי	 154
+קע	 153
+ונ	 153
+�ע	 153
+�נ	 153
+_װא	 152
+�י�	 152
+ני�	 152
+�ן	 151
+ין	 151
+אױ	 151
+�ױ	 151
+י�	 150
+�ט	 150
+�	 150
+��	 150
+יִ	 150
+�ִ	 150
+ִ	 150
+ַט	 150
+ִ�	 149
+�ִ�	 149
+��	 149
+יִ�	 149
+�י�	 148
+_י�	 148
+לי�	 148
+�ױ�	 146
+אױ�	 146
+�ַנ	 146
+_אױ	 145
+�ון	 145
+יז	 143
+�ז	 143
+�י�	 142
+די�	 142
diff --git a/libtextcat/prj/d.lst b/libtextcat/prj/d.lst
index 44ce02b77c44..3dba0640e738 100644
--- a/libtextcat/prj/d.lst
+++ b/libtextcat/prj/d.lst
@@ -6,3 +6,7 @@
 mkdir: %_DEST%\inc%_EXT%\libtextcat
 hedabu: ..\%__SRC%\misc\build\libtextcat-2.2\src\*.h %_DEST%\inc%_EXT%\libtextcat\*.h
 
+# data for language guessing
+..\data\new_fingerprints\fpdb.conf %COMMON_DEST%\pck%_EXT%\fpdb.conf
+..\data\new_fingerprints\lm\*.lm   %COMMON_DEST%\pck%_EXT%\*.lm
+
author	Thomas Lange <tl@openoffice.org>	2007-01-12 11:57:30 +0000
committer	Thomas Lange <tl@openoffice.org>	2007-01-12 11:57:30 +0000
commit	0b876445efbd93c73879c216d564c0508cea530f (patch)
tree	651fb2e3093ff5e3d5ad4afb9ba20435e42ed862 /libtextcat
parent	23147b5b1f280e1c7758c4ce27b99dc92135b354 (diff)