diff options
Diffstat (limited to 'libtextcat/data/new_fingerprints/lm/serbian-latin.lm')
-rw-r--r-- | libtextcat/data/new_fingerprints/lm/serbian-latin.lm | 400 |
1 files changed, 400 insertions, 0 deletions
diff --git a/libtextcat/data/new_fingerprints/lm/serbian-latin.lm b/libtextcat/data/new_fingerprints/lm/serbian-latin.lm new file mode 100644 index 000000000000..0a028311a030 --- /dev/null +++ b/libtextcat/data/new_fingerprints/lm/serbian-latin.lm @@ -0,0 +1,400 @@ +_ 56298 +a 17374 +i 15500 +e 13745 +o 13087 +n 9704 +r 8535 +s 7383 +t 6692 +j 6664 +u 6390 +k 6060 +a_ 5221 +v 5177 +l 5082 +d 4923 +e_ 4729 +m 4663 +p 4121 +i_ 3992 +_s 2964 +je 2847 +g 2703 +z 2575 +u_ 2521 +_p 2491 +ra 2430 +_i 2355 +na 2337 +. 2169 +, 2142 +,_ 2134 +._ 2112 +st 2091 +o_ 2004 +ni 1971 +b 1933 +ko 1894 +je_ 1700 +an 1671 +ij 1628 +no 1559 +č 1550 +_n 1522 +_u 1516 +re 1465 +ti 1409 +_o 1368 +en 1365 +_k 1353 +_j 1346 +_d 1341 +ja 1325 +li 1314 +ta 1309 +pr 1303 +c 1287 +ka 1269 +_je 1233 +po 1224 +ne 1221 +_i_ 1220 +ri 1198 +va 1197 +ov 1151 +od 1146 +la 1139 +sk 1132 +m_ 1124 +_pr 1120 +os 1086 +in 1060 +š 1053 +ve 1048 +oj 1035 +ma 1029 +om 1027 +og 1024 +im 1006 +av 1002 +al 982 +me 976 +vi 971 +_po 966 +_na 963 +na_ 944 +da 928 +ro 905 +nj 900 +ik 891 +_je_ 889 +to 884 +ad 881 +ar 873 +h 862 +or 858 +se 840 +_m 836 +te 819 +is 816 +_u_ 810 +aj 809 +ed 800 +_t 791 +et 772 +at 740 +vo 735 +ju 731 +gr 723 +di 722 +lo 722 +za 709 +il 709 +ak 707 +_r 704 +ja_ 703 +ji 700 +ne_ 694 +_ko 691 +ki 689 +er 681 +ci 680 +ć 673 +_se 670 +_v 664 +ž 663 +el 662 +on 658 +_z 656 +S 638 +iz 635 +bi 622 +ek 616 +_S 612 +su 607 +gra 606 +sa 603 +a, 601 +a,_ 598 +_b 598 +ih 597 +om_ 591 +_g 588 +ost 587 +ije 586 +d_ 579 +tr 574 +se_ 567 +ija 561 +de 559 +em 552 +_se_ 552 +le 549 +a. 548 +lj 548 +a._ 542 +do 540 +_su 533 +zi 529 +ič 525 +sta 520 +h_ 520 +ke 517 +ih_ 511 +f 507 +go 505 +ol 504 +dn 498 +sti 496 +ka_ 493 +_. 489 +_._ 473 +rad 472 +_a 468 +g_ 463 +ic 461 +as 461 +_za 461 +it 456 +koj 454 +ob 448 +iv 442 +da_ 442 +az 441 +su_ 436 +ku 433 +ma_ 430 +mo 429 +ju_ 429 +_sa 427 +ke_ 421 +ni_ 421 +ist 421 +og_ 418 +_od 417 +am 416 +anj 412 +đ 407 +_su_ 407 +ru 400 +nje 398 +sl 397 +ok 392 +op 391 +_koj 391 +_na_ 389 +tn 388 +ji_ 384 +e, 383 +_do 381 +e,_ 380 +ima 379 +ač 378 +nos 378 +vn 377 +B 377 +_ka 373 +ti_ 372 +li_ 370 +eo 370 +pre 367 +_iz 364 +P 361 +sko 361 +io 360 +n_ 360 +" 356 +vr 354 +_st 354 +mi 352 +čk 351 +ao 350 +im_ 347 +es 346 +_B 346 +ev 344 +ski 343 +ez 343 +j_ 341 +ije_ 341 +ig 339 +_ra 338 +ko_ 336 +tv 336 +grad 335 +no_ 335 +la_ 334 +_P 333 +_da 333 +št 332 +od_ 330 +- 326 +dr 323 +va_ 322 +tu 320 +_l 316 +pro 315 +ori 315 +N 314 +ika 311 +ija_ 311 +sto 309 +e. 307 +ir 303 +e._ 302 +_pro 301 +_pre 300 +ki_ 300 +ot 299 +_N 297 +sv 294 +pe 291 +ns 291 +sn 291 +met 290 +t_ 289 +pri 289 +ba 288 +ili 288 +pa 288 +ut 287 +ao_ 286 +oji 285 +_ne 285 +če 284 +ova 283 +kom 282 +um 281 +ičk 279 +nost 279 +k_ 279 +si 279 +ada 278 +van 278 +cij 276 +Sr 276 +lik 275 +_Sr 275 +nt 275 +ogr 274 +ug 274 +_ve 274 +ran 273 +br 273 +ani 272 +ine 272 +ac 271 +edn 271 +red 268 +_bi 266 +_pri 266 +ud 266 +ogra 265 +nja 265 +odi 264 +_f 263 +_re 262 +ga 258 +ati 258 +zn 257 +ovi 255 +rij 254 +_sv 254 +ako 252 +nu 252 +nij 251 +ana 251 +ča 251 +rav 250 +din 248 +kr 247 +iš 247 +či 245 +up 245 +ce 245 +ta_ 244 +rv 244 +men 244 +un 243 +rb 243 +aju 241 +ava 241 +ra_ 241 +etn 239 +oj_ 239 +ln 238 +T 238 +pos 237 +eni 237 +M 234 +_go 233 +_od_ 232 +du 231 +ali 231 +ini 229 +ima_ 229 +_da_ 228 +nov 227 +_te 227 +ps 225 +_e 225 +Srb 223 +ca 223 +_M 223 +_Srb 222 +ara 222 +_mo 221 +Be 221 +_de 221 +i. 220 +bij 220 +K 220 +jed 219 +sa_ 219 +oji_ 218 +čn 218 +_ob 218 +pi 218 +ur 218 +eogr 217 +ove 217 +avi 217 +tno 217 +eog 217 +eogra 217 +stv 216 +zv 216 +_Be 216 +i._ 216 +nik 215 +bo 214 +_koji 214 +nic 214 +koji 214 +_pos 214 +_K 213 +ume 213 +za_ 211 +i, 211 +i,_ 211 |