diff options
Diffstat (limited to 'libtextcat/data/new_fingerprints/lm/catalan.lm')
-rw-r--r-- | libtextcat/data/new_fingerprints/lm/catalan.lm | 400 |
1 files changed, 400 insertions, 0 deletions
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 |