summaryrefslogtreecommitdiff
path: root/libtextcat/data/new_fingerprints/lm/indonesian.lm
diff options
context:
space:
mode:
Diffstat (limited to 'libtextcat/data/new_fingerprints/lm/indonesian.lm')
-rw-r--r--libtextcat/data/new_fingerprints/lm/indonesian.lm400
1 files changed, 400 insertions, 0 deletions
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