language_detector 0.1.0

data/lib/textcat_ngrams/slovak-windows1250.lm

@@ -0,0 +1,400 @@
+_	 8202
+o	 2145
+a	 1912
+e	 1763
+i	 1491
+n	 1415
+r	 1256
+t	 1127
+v	 1080
+s	 1004
+k	 824
+d	 739
+p	 739
+l	 735
+m	 685
+c	 620
+u	 597
+h	 531
+a_	 467
+j	 449
+_p	 445
+z	 439
+e_	 412
+�	 402
+_v	 369
+.	 361
+_s	 359
+ov	 330
+b	 327
+st	 312
+y	 309
+pr	 307
+._	 300
+o_	 297
+�	 278
+,	 268
+,_	 260
+to	 258
+�	 256
+_a	 254
+�	 253
+i_	 252
+_pr	 246
+ch	 242
+re	 233
+_z	 223
+ra	 220
+_n	 217
+ne	 214
+ie	 214
+po	 214
+en	 208
+ro	 205
+or	 204
+�	 199
+u_	 197
+an	 197
+ko	 194
+na	 189
+ni	 187
+va	 183
+�	 182
+�	 180
+os	 179
+v_	 176
+�	 173
+_o	 171
+ho	 170
+ia	 168
+no	 166
+li	 166
+h_	 166
+ed	 164
+j_	 161
+om	 160
+_k	 160
+�	 158
+ch_	 158
+ti	 155
+y_	 148
+m_	 147
+ej	 147
+_po	 145
+ci	 145
+_d	 140
+�_	 139
+do	 138
+_t	 137
+_m	 134
+ri	 129
+mi	 129
+od	 128
+te	 124
+_a_	 124
+la	 122
+al	 121
+aj	 120
+ej_	 120
+vo	 119
+ol	 119
+in	 118
+ve	 117
+me	 117
+tr	 116
+sk	 116
+ova	 116
+S	 111
+er	 110
+ob	 110
+_na	 109
+ad	 107
+je	 106
+at	 104
+_v_	 103
+_r	 102
+ic	 101
+�ch	 100
+pre	 100
+�c	 100
+av	 98
+es	 96
+ta	 95
+dn	 94
+ho_	 94
+lo	 94
+�_	 93
+_pre	 93
+it	 93
+V	 92
+de	 92
+kt	 89
+n�	 89
+za	 88
+A	 87
+le	 86
+�ch_	 86
+ok	 86
+ost	 85
+vi	 84
+ie_	 83
+ak	 82
+P	 82
+n�	 81
+R	 80
+sa	 80
+as	 79
+�i	 78
+na_	 77
+a�	 77
+�_	 77
+�	 76
+ar	 75
+di	 75
+_S	 74
+om_	 74
+_V	 73
+_do	 73
+_za	 72
+-	 72
+ck	 71
+vy	 71
+ka	 71
+f	 70
+tor	 70
+am	 70
+on	 70
+_-	 69
+_P	 69
+M	 68
+_i	 68
+_sa	 68
+nos	 68
+n�	 68
+�c	 67
+a�_	 67
+sl	 66
+il	 66
+r�	 66
+_c	 66
+_b	 66
+_-_	 64
+sa_	 64
+-_	 64
+kto	 64
+_j	 64
+ani	 64
+kr	 64
+sti	 63
+ou	 63
+ot	 63
+ne_	 63
+_sa_	 62
+v�	 62
+_na_	 62
+red	 62
+ku	 61
+is	 61
+n�	 60
+�_	 60
+so	 60
+sp	 60
+_st	 59
+g	 59
+tn	 59
+str	 58
+�e	 58
+nt	 58
+et	 57
+pra	 57
+ke	 57
+ov_	 57
+_vy	 57
+_M	 57
+nej	 56
+tu	 56
+l_	 56
+_je	 56
+nie	 56
+�n	 56
+k_	 56
+pe	 56
+_h	 55
+oz	 55
+�_	 55
+est	 55
+_�	 55
+va�	 55
+ma	 54
+n�_	 53
+t�	 53
+..	 53
+r�	 52
+ran	 52
+bo	 51
+nej_	 51
+ick	 51
+ti_	 51
+ia_	 51
+ktor	 51
+K	 51
+O	 51
+T	 51
+_ne	 51
+ou_	 50
+I	 50
+oc	 50
+to_	 50
+vn	 50
+sta	 50
+_.	 50
+da	 50
+�h	 49
+�ho	 49
+N	 49
+_ro	 49
+_ko	 49
+ac	 49
+ek	 49
+li_	 49
+�a	 49
+rov	 49
+oj	 48
+s_	 48
+s�	 48
+�ho_	 48
+va�_	 48
+je_	 48
+z�	 47
+ik	 47
+mo	 47
+mi_	 47
+si	 47
+_kto	 46
+_sp	 46
+_kt	 46
+E	 46
+_ktor	 46
+eb	 46
+n�c	 45
+_u	 45
+el	 45
+B	 45
+n�ch	 45
+pro	 45
+eni	 44
+_�	 44
+em	 44
+kon	 44
+pa	 44
+ky	 44
+uj	 44
+�e_	 44
+ova�	 44
+cie	 44
+hr	 44
+k�	 44
+n�ch_	 43
+pred	 43
+zo	 43
+ln	 43
+o�	 43
+tov	 43
+nu	 43
+e�	 43
+�c	 42
+�l	 42
+�m	 42
+pri	 42
+_to	 42
+l�	 41
+ce	 41
+�v	 41
+eh	 41
+_pro	 41
+rav	 41
+kej	 41
+ns	 41
+ali	 41
+oli	 40
+�_	 40
+_pri	 40
+oh	 40
+ud	 40
+_ak	 40
+ent	 40
+e�	 40
+prav	 39
+_pred	 39
+�i	 39
+zn	 39
+ny	 39
+ove	 39
+pol	 39
+ru	 39
+a,	 39
+ah	 39
+kej_	 39
+a,_	 38
+z_	 38
+aj_	 38
+r_	 38
+i�	 38
+ova�_	 38
+tre	 38
+pod	 37
+_z�	 37
+_ob	 37
+nost	 37
+sti_	 37
+van	 37
+up	 37
+osti	 36
+�ci	 36
+_�e	 36
+j�	 36
+co	 36
+_str	 36
+�i	 36
+_ma	 36
+ut	 36
+nsk	 36
+by	 36
+_ve	 35
+ko_	 35
+de_	 35
+�ia	 35
+_aj	 35
+_aj_	 35
+op	 35
+_pod	 34
+pr�	 34
+_in	 34
+ez	 34
+odn	 34
+dne	 34
+Z	 34
+tra	 34
+bn	 34
+�d	 34
+_�e_	 34
+_vo	 34
+�as	 34
+�t	 34
+d_	 34
+�	 34
+sto	 34
+ky_	 34
+ir	 33
+_z_	 33
+nie_	 33
+�t	 33
+ven	 33
+i�_	 33
+_s_	 33
+_B	 33
+�e	 33
+ens	 33
+spo	 32
+eho	 32
+lad	 32

data/lib/textcat_ngrams/slovenian-ascii.lm

@@ -0,0 +1,400 @@
+_	 25262
+e	 6217
+a	 5964
+i	 5611
+o	 5538
+n	 4132
+s	 3349
+l	 3268
+r	 2913
+t	 2777
+j	 2672
+v	 2282
+k	 2175
+e_	 1958
+d	 1953
+p	 1786
+a_	 1700
+y	 1623
+m	 1559
+o_	 1542
+z	 1521
+i_	 1462
+_s	 1433
+je	 1383
+,	 1278
+,_	 1278
+b	 1230
+c	 1137
+_p	 1130
+_n	 1032
+je_	 997
+u	 986
+_j	 972
+g	 933
+_je	 877
+cy	 848
+_je_	 842
+_v	 793
+il	 786
+ni	 782
+st	 779
+na	 743
+ra	 726
+.	 723
+._	 716
+_z	 713
+in	 691
+_k	 685
+_b	 667
+al	 640
+h	 627
+po	 607
+ti	 584
+pr	 584
+ko	 584
+_d	 582
+el	 579
+n_	 579
+la	 577
+lo	 573
+l_	 571
+_t	 567
+se	 567
+ne	 562
+_i	 556
+no	 549
+en	 546
+_o	 534
+re	 524
+bi	 514
+li	 512
+ov	 496
+sy	 458
+_na	 457
+te	 453
+da	 451
+_po	 440
+_bi	 437
+ye	 436
+to	 424
+ri	 420
+an	 420
+_pr	 417
+ve	 410
+nj	 404
+ka	 403
+_m	 394
+le	 385
+ja	 377
+va	 374
+de	 374
+is	 371
+ed	 364
+v_	 362
+za	 361
+in_	 354
+bil	 353
+_se	 351
+aj	 347
+ga	 344
+ar	 343
+od	 339
+_in	 338
+_in_	 333
+tr	 332
+os	 332
+_bil	 332
+ta	 328
+vo	 327
+ki	 324
+ro	 324
+et	 320
+so	 315
+em	 313
+lo_	 311
+na_	 306
+av	 305
+ih	 305
+yi	 304
+h_	 295
+at	 294
+m_	 293
+ek	 292
+ol	 289
+se_	 289
+as	 284
+lj	 281
+_za	 277
+ob	 275
+om	 273
+me	 273
+zy	 272
+mi	 268
+eg	 265
+_v_	 263
+_g	 260
+or	 260
+es	 259
+_se_	 258
+do	 255
+ni_	 255
+ga_	 253
+oc	 251
+il_	 250
+vi	 249
+ak	 248
+no_	 243
+da_	 241
+pa	 240
+_ne	 238
+ot	 238
+_so	 238
+ocy	 237
+ya	 237
+la_	 234
+li_	 234
+ih_	 231
+_c	 229
+az	 229
+ik	 228
+on	 225
+ki_	 224
+go	 223
+im	 223
+sk	 223
+mo	 221
+cye	 219
+ti_	 217
+ji	 216
+_da	 216
+iz	 215
+ko_	 214
+ic	 213
+_l	 209
+u_	 209
+pre	 208
+_r	 208
+_ko	 208
+t_	 207
+z_	 206
+er	 206
+so_	 206
+ilo	 203
+r_	 201
+j_	 199
+ad	 195
+cyi	 193
+_na_	 193
+sa	 191
+ev	 191
+i,	 188
+i,_	 188
+it	 187
+sto	 186
+_da_	 184
+_ni	 183
+_so_	 182
+_ve	 182
+nje	 181
+a,	 181
+kr	 181
+a,_	 181
+dn	 177
+_st	 177
+di	 176
+ega	 176
+og	 174
+o,_	 174
+o,	 174
+ilo_	 172
+_ki	 171
+ma	 170
+-	 170
+ij	 169
+_cy	 169
+ost	 169
+e,	 168
+e,_	 168
+ne_	 168
+ok	 166
+ke	 165
+_pre	 165
+del	 165
+yn	 165
+al_	 165
+bo	 164
+_pa	 163
+_ki_	 163
+am	 159
+ns	 158
+ye_	 156
+sp	 155
+em_	 154
+_ka	 154
+_te	 153
+_iz	 152
+ega_	 151
+_ob	 150
+br	 149
+ec	 149
+pri	 148
+ap	 147
+ez	 147
+ali	 147
+raz	 144
+jo	 142
+to_	 141
+d_	 138
+a._	 137
+a.	 137
+cya	 137
+ova	 136
+anj	 136
+el_	 135
+V	 135
+si	 134
+sta	 134
+_pri	 132
+_to	 131
+_a	 130
+_bilo	 130
+bilo	 130
+oj	 129
+ecy	 128
+_od	 128
+gl	 128
+op	 127
+ju	 127
+rav	 126
+_u	 125
+s_	 125
+_V	 125
+ila	 125
+ce	 124
+_mo	 124
+ali_	 124
+ah	 122
+str	 122
+_sp	 121
+vr	 121
+aj_	 121
+_do	 121
+bilo_	 121
+N	 119
+iv	 117
+ru	 116
+vs	 116
+jal	 116
+pi	 115
+O	 115
+_z_	 113
+icy	 112
+k_	 112
+be	 112
+elo	 111
+dr	 110
+pra	 110
+sye	 110
+ved	 109
+rs	 108
+_tr	 108
+tv	 108
+oz	 108
+tn	 107
+_nj	 107
+le_	 107
+_N	 107
+_ni_	 106
+pa_	 106
+l,_	 105
+l,	 105
+ins	 105
+ako	 104
+ac	 104
+ist	 104
+ir	 104
+sl	 104
+ila_	 103
+nik	 103
+bi_	 103
+i.	 102
+i._	 102
+_vs	 102
+iti	 102
+_sy	 101
+P	 101
+val	 100
+ku	 100
+_P	 99
+pe	 99
+ala	 99
+bil_	 98
+eli	 98
+jen	 98
+ede	 98
+_zy	 98
+T	 96
+ja_	 96
+ran	 95
+_bo	 95
+S	 95
+ln	 95
+zn	 94
+nst	 93
+_pa_	 93
+_ra	 93
+_bil_	 93
+nil	 93
+ati	 92
+ej	 92
+ocyi	 92
+e.	 91
+_le	 91
+ud	 91
+nov	 91
+nja	 91
+sn	 91
+ar_	 91
+e._	 91
+kl	 91
+isy	 90
+zye	 90
+en_	 90
+sti	 90
+_ga	 90
+prav	 90
+_bi_	 90
+za_	 89
+lik	 89
+ton	 89
+kra	 88
+rt	 88
+W	 88
+_de	 88
+_ga_	 88
+M	 88
+ep	 87
+cyn	 87
+Wi	 87
+_S	 87
+ut	 87
+_W	 87
+inst	 87
+insto	 86
+ste	 86
+Wins	 86
+gov	 86
+nu	 86
+Win	 86
+_Wi	 86
+Winst	 86
+nsto	 86
+eti	 86
+ston	 86
+nston	 86
+_Win	 85
+_Wins	 85
+ili	 84
+bra	 83
+rat	 83