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