Upload /content/models/baoule_tokenizer.vocab with huggingface_hub

content/models/baoule_tokenizer.vocab

@@ -0,0 +1,507 @@
+[\u0000] 0
+[\u0001] 1
+[\u0002] 2
+[\u0003] 3
+[\u0004] 4
+[\u0005] 5
+[\u0006] 6
+[\u0007] 7
+[\u0008] 8
+[\u0009] 9
+[\u000a] 10
+[\u000b] 11
+[\u000c] 12
+[\u000d] 13
+[\u000e] 14
+[\u000f] 15
+[\u0010] 16
+[\u0011] 17
+[\u0012] 18
+[\u0013] 19
+[\u0014] 20
+[\u0015] 21
+[\u0016] 22
+[\u0017] 23
+[\u0018] 24
+[\u0019] 25
+[\u001a] 26
+[\u001b] 27
+[\u001c] 28
+[\u001d] 29
+[\u001e] 30
+[\u001f] 31
+[ ] 32
+[!] 33
+["] 34
+[#] 35
+[$] 36
+[%] 37
+[&] 38
+['] 39
+[(] 40
+[)] 41
+[*] 42
+[+] 43
+[,] 44
+[-] 45
+[.] 46
+[/] 47
+[0] 48
+[1] 49
+[2] 50
+[3] 51
+[4] 52
+[5] 53
+[6] 54
+[7] 55
+[8] 56
+[9] 57
+[:] 58
+[;] 59
+[<] 60
+[=] 61
+[>] 62
+[?] 63
+[@] 64
+[A] 65
+[B] 66
+[C] 67
+[D] 68
+[E] 69
+[F] 70
+[G] 71
+[H] 72
+[I] 73
+[J] 74
+[K] 75
+[L] 76
+[M] 77
+[N] 78
+[O] 79
+[P] 80
+[Q] 81
+[R] 82
+[S] 83
+[T] 84
+[U] 85
+[V] 86
+[W] 87
+[X] 88
+[Y] 89
+[Z] 90
+[[] 91
+[\] 92
+[]] 93
+[^] 94
+[_] 95
+[`] 96
+[a] 97
+[b] 98
+[c] 99
+[d] 100
+[e] 101
+[f] 102
+[g] 103
+[h] 104
+[i] 105
+[j] 106
+[k] 107
+[l] 108
+[m] 109
+[n] 110
+[o] 111
+[p] 112
+[q] 113
+[r] 114
+[s] 115
+[t] 116
+[u] 117
+[v] 118
+[w] 119
+[x] 120
+[y] 121
+[z] 122
+[{] 123
+[|] 124
+[}] 125
+[~] 126
+[\u007f] 127
+[�] 128
+[�] 129
+[�] 130
+[�] 131
+[�] 132
+[�] 133
+[�] 134
+[�] 135
+[�] 136
+[�] 137
+[�] 138
+[�] 139
+[�] 140
+[�] 141
+[�] 142
+[�] 143
+[�] 144
+[�] 145
+[�] 146
+[�] 147
+[�] 148
+[�] 149
+[�] 150
+[�] 151
+[�] 152
+[�] 153
+[�] 154
+[�] 155
+[�] 156
+[�] 157
+[�] 158
+[�] 159
+[�] 160
+[�] 161
+[�] 162
+[�] 163
+[�] 164
+[�] 165
+[�] 166
+[�] 167
+[�] 168
+[�] 169
+[�] 170
+[�] 171
+[�] 172
+[�] 173
+[�] 174
+[�] 175
+[�] 176
+[�] 177
+[�] 178
+[�] 179
+[�] 180
+[�] 181
+[�] 182
+[�] 183
+[�] 184
+[�] 185
+[�] 186
+[�] 187
+[�] 188
+[�] 189
+[�] 190
+[�] 191
+[�] 192
+[�] 193
+[�] 194
+[�] 195
+[�] 196
+[�] 197
+[�] 198
+[�] 199
+[�] 200
+[�] 201
+[�] 202
+[�] 203
+[�] 204
+[�] 205
+[�] 206
+[�] 207
+[�] 208
+[�] 209
+[�] 210
+[�] 211
+[�] 212
+[�] 213
+[�] 214
+[�] 215
+[�] 216
+[�] 217
+[�] 218
+[�] 219
+[�] 220
+[�] 221
+[�] 222
+[�] 223
+[�] 224
+[�] 225
+[�] 226
+[�] 227
+[�] 228
+[�] 229
+[�] 230
+[�] 231
+[�] 232
+[�] 233
+[�] 234
+[�] 235
+[�] 236
+[�] 237
+[�] 238
+[�] 239
+[�] 240
+[�] 241
+[�] 242
+[�] 243
+[�] 244
+[�] 245
+[�] 246
+[�] 247
+[�] 248
+[�] 249
+[�] 250
+[�] 251
+[�] 252
+[�] 253
+[�] 254
+[�] 255
+[ɛ] 256
+[ɔ] 257
+[ŋ] 258
+[ɲ] 259
+[�][�] -> [�] 265
+[�][�] -> [’] 266
+[a][n] -> [an] 267
+[ ][n] -> [ n] 268
+[’][n] -> [’n] 269
+[ ][k] -> [ k] 270
+[ ][b] -> [ b] 271
+[ ][s] -> [ s] 272
+[u][n] -> [un] 273
+[ b][e] -> [ be] 274
+[ ][i] -> [ i] 275
+[i][n] -> [in] 276
+[l][i] -> [li] 277
+[ ][m] -> [ m] 278
+[ ][y] -> [ y] 279
+[ ][w] -> [ w] 280
+[ɛ][n] -> [ɛn] 281
+[ ][ɔ] -> [ ɔ] 282
+[l][ɛ] -> [lɛ] 283
+[ ][t] -> [ t] 284
+[ ][a] -> [ a] 285
+[ ][f] -> [ f] 286
+[ k][ɛ] -> [ kɛ] 287
+[ n][g] -> [ ng] 288
+[ s][u] -> [ su] 289
+[ n][un] -> [ nun] 290
+[ ][e] -> [ e] 291
+[l][a] -> [la] 292
+[u][ɛ] -> [uɛ] 293
+[a][an] -> [aan] 294
+[ n][in] -> [ nin] 295
+[ t][i] -> [ ti] 296
+[ y][ɛ] -> [ yɛ] 297
+[l][e] -> [le] 298
+[i][e] -> [ie] 299
+[ ng][a] -> [ nga] 300
+[f][uɛ] -> [fuɛ] 301
+[ k][p] -> [ kp] 302
+[r][an] -> [ran] 303
+[m][an] -> [man] 304
+[’][m] -> [’m] 305
+[i][ɛn] -> [iɛn] 306
+[an][n] -> [ann] 307
+[ ][�] -> [ �] 308
+[ f][a] -> [ fa] 309
+[ y][o] -> [ yo] 310
+[m][iɛn] -> [miɛn] 311
+[ ][d] -> [ d] 312
+[ k][un] -> [ kun] 313
+[ w][un] -> [ wun] 314
+[ ][li] -> [ li] 315
+[d][ɛ] -> [dɛ] 316
+[’][ɔ] -> [’ɔ] 317
+[ ][Z] -> [ Z] 318
+[ ][�] -> [ �] 319
+[l][o] -> [lo] 320
+[ s][ran] -> [ sran] 321
+[ k][w] -> [ kw] 322
+[ s][a] -> [ sa] 323
+[�][�] -> [á] 324
+[an][miɛn] -> [anmiɛn] 325
+[ s][ɔ] -> [ sɔ] 326
+[ ][j] -> [ j] 327
+[ kw][la] -> [ kwla] 328
+[ b][o] -> [ bo] 329
+[�][anmiɛn] -> [�anmiɛn] 330
+[l][u] -> [lu] 331
+[ɔ][n] -> [ɔn] 332
+[ m][ɔ] -> [ mɔ] 333
+[ kp][a] -> [ kpa] 334
+[m][un] -> [mun] 335
+[ li][k] -> [ lik] 336
+[�][�] -> [é] 337
+[ �][�anmiɛn] -> [ Ɲanmiɛn] 338
+[n][g] -> [ng] 339
+[ n][aan] -> [ naan] 340
+[’][a] -> [’a] 341
+[ m][un] -> [ mun] 342
+[u][e] -> [ue] 343
+[ n][dɛ] -> [ ndɛ] 344
+[�][�] -> [”] 345
+[ s][e] -> [ se] 346
+[ w][ie] -> [ wie] 347
+[ �][�] -> [ “] 348
+[r][a] -> [ra] 349
+[l][ɔ] -> [lɔ] 350
+[�][�] -> [́] 351
+[ ][c] -> [ c] 352
+[ a][mun] -> [ amun] 353
+[ d][i] -> [ di] 354
+[ ][o] -> [ o] 355
+[ lik][e] -> [ like] 356
+[ ][ɲ] -> [ ɲ] 357
+[ ][K] -> [ K] 358
+[ ][an] -> [ an] 359
+[ann][g] -> [anng] 360
+[ �][�] -> [ ‘] 361
+[o][v] -> [ov] 362
+[ov][a] -> [ova] 363
+[o][ova] -> [oova] 364
+[ ][B] -> [ B] 365
+[ ][S] -> [ S] 366
+[k][un] -> [kun] 367
+[ ][A] -> [ A] 368
+[ m][aan] -> [ maan] 369
+[ w][a] -> [ wa] 370
+[z][i] -> [zi] 371
+[ s][ɛ] -> [ sɛ] 372
+[ Z][oova] -> [ Zoova] 373
+[ ][M] -> [ M] 374
+[u][a] -> [ua] 375
+[ s][i] -> [ si] 376
+[ ][N] -> [ N] 377
+[ ][lɔ] -> [ lɔ] 378
+[n][in] -> [nin] 379
+[ k][le] -> [ kle] 380
+[ n][i] -> [ ni] 381
+[ m][in] -> [ min] 382
+[u][an] -> [uan] 383
+[ f][ɛ] -> [ fɛ] 384
+[w][lɛ] -> [wlɛ] 385
+[un][man] -> [unman] 386
+[a][s] -> [as] 387
+[ ][le] -> [ le] 388
+[á][n] -> [án] 389
+[ m][m] -> [ mm] 390
+[t][i] -> [ti] 391
+[ y][i] -> [ yi] 392
+[ b][é] -> [ bé] 393
+[ a][s] -> [ as] 394
+[.][”] -> [.”] 395
+[b][lu] -> [blu] 396
+[e][zi] -> [ezi] 397
+[ann][in] -> [annin] 398
+[ k][o] -> [ ko] 399
+[ se][li] -> [ seli] 400
+[ a][w] -> [ aw] 401
+[ s][ie] -> [ sie] 402
+[ kwla][a] -> [ kwlaa] 403
+[z][ɛ] -> [zɛ] 404
+[i][ɛ] -> [iɛ] 405
+[t][a] -> [ta] 406
+[u][s] -> [us] 407
+[f][a] -> [fa] 408
+[ n][n] -> [ nn] 409
+[c][i] -> [ci] 410
+[ Z][ezi] -> [ Zezi] 411
+[ k][l] -> [ kl] 412
+[k][a] -> [ka] 413
+[K][ɛ] -> [Kɛ] 414
+[.][’] -> [.’] 415
+[ng][e] -> [nge] 416
+[ k][an] -> [ kan] 417
+[ ][?] -> [ ?] 418
+[�][�] -> [ó] 419
+[ s][in] -> [ sin] 420
+[ann][zɛ] -> [annzɛ] 421
+[�][�] -> [í] 422
+[�][�] -> [ú] 423
+[ b][a] -> [ ba] 424
+[ m][an] -> [ man] 425
+[ c][ɛn] -> [ cɛn] 426
+[ ][I] -> [ I] 427
+[ b][u] -> [ bu] 428
+[�][�] -> [—] 429
+[anng][ɛ] -> [anngɛ] 430
+[ ][la] -> [ la] 431
+[ n][z] -> [ nz] 432
+[w][a] -> [wa] 433
+[i][blu] -> [iblu] 434
+[ t][ɛ] -> [ tɛ] 435
+[ b][la] -> [ bla] 436
+[ li][ɛ] -> [ liɛ] 437
+[ M][un] -> [ Mun] 438
+[ yo][li] -> [ yoli] 439
+[l][ɛn] -> [lɛn] 440
+[�][�] -> [Ɔ] 441
+[i][a] -> [ia] 442
+[ m][ɛn] -> [ mɛn] 443
+[ ][g] -> [ g] 444
+[ w][la] -> [ wla] 445
+[ k][lo] -> [ klo] 446
+[ b][ɔ] -> [ bɔ] 447
+[ yɛ][le] -> [ yɛle] 448
+[ y][a] -> [ ya] 449
+[b][a] -> [ba] 450
+[ f][i] -> [ fi] 451
+[ kp][ɛ] -> [ kpɛ] 452
+[ t][ra] -> [ tra] 453
+[k][p] -> [kp] 454
+[ w][aan] -> [ waan] 455
+[ nin][nge] -> [ ninnge] 456
+[ B][iblu] -> [ Biblu] 457
+[ fa][ta] -> [ fata] 458
+[an][man] -> [anman] 459
+[n][d] -> [nd] 460
+[ ɲ][in] -> [ ɲin] 461
+[ ][Y] -> [ Y] 462
+[ ɔ][n] -> [ ɔn] 463
+[j][a] -> [ja] 464
+[ ][annzɛ] -> [ annzɛ] 465
+[us][u] -> [usu] 466
+[ ][F] -> [ F] 467
+[r][ɛ] -> [rɛ] 468
+[m][ɛn] -> [mɛn] 469
+[s][an] -> [san] 470
+[ �][�] -> [ Ɔ] 471
+[ ][u] -> [ u] 472
+[f][i] -> [fi] 473
+[li][ɛ] -> [liɛ] 474
+[ y][ó] -> [ yó] 475
+[ t][ran] -> [ tran] 476
+[n][dɛ] -> [ndɛ] 477
+[ j][unman] -> [ junman] 478
+[ lik][a] -> [ lika] 479
+[s][t] -> [st] 480
+[ d][an] -> [ dan] 481
+[a][t] -> [at] 482
+[ ][é] -> [ é] 483
+[ ][lɛ] -> [ lɛ] 484
+[ n][uan] -> [ nuan] 485
+[ j][as] -> [ jas] 486
+[ ni][an] -> [ nian] 487
+[ k][ɔ] -> [ kɔ] 488
+[ k][a] -> [ ka] 489
+[nd][an] -> [ndan] 490
+[ kl][un] -> [ klun] 491
+[ a][f] -> [ af] 492
+[an][wlɛ] -> [anwlɛ] 493
+[li][st] -> [list] 494
+[i][an] -> [ian] 495
+[ ][E] -> [ E] 496
+[S][ɛ] -> [Sɛ] 497
+[ di][lɛ] -> [ dilɛ] 498
+[ b][lɛ] -> [ blɛ] 499
+[n][j] -> [nj] 500
+[ f][lɛ] -> [ flɛ] 501
+[ a][t] -> [ at] 502
+[ wa][fa] -> [ wafa] 503
+[ jas][in] -> [ jasin] 504
+[ t][a] -> [ ta] 505
+[ɛ][li] -> [ɛli] 506
+[a][m] -> [am] 507
+[ n][án] -> [ nán] 508
+[ ɲ][r] -> [ ɲr] 509
+[ K][ɛ] -> [ Kɛ] 510
+[ ][D] -> [ D] 511