voidful commited on
Commit
8e8967d
1 Parent(s): 570ea52

add tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer_config.json +11 -0
  3. vocab.json +532 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "[UNK]"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "do_lower_case": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "[PAD]",
7
+ "replace_word_delimiter_char": " ",
8
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
9
+ "unk_token": "[UNK]",
10
+ "word_delimiter_token": "|"
11
+ }
vocab.json ADDED
@@ -0,0 +1,532 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "0": 59,
3
+ "1": 299,
4
+ "10": 20,
5
+ "100": 315,
6
+ "101": 321,
7
+ "102": 46,
8
+ "103": 332,
9
+ "104": 335,
10
+ "105": 467,
11
+ "106": 495,
12
+ "107": 30,
13
+ "108": 145,
14
+ "109": 202,
15
+ "11": 35,
16
+ "110": 385,
17
+ "111": 207,
18
+ "112": 366,
19
+ "113": 121,
20
+ "114": 109,
21
+ "115": 16,
22
+ "116": 57,
23
+ "117": 451,
24
+ "118": 224,
25
+ "119": 282,
26
+ "12": 496,
27
+ "120": 501,
28
+ "121": 408,
29
+ "122": 484,
30
+ "123": 235,
31
+ "124": 485,
32
+ "125": 173,
33
+ "126": 176,
34
+ "127": 137,
35
+ "128": 374,
36
+ "129": 236,
37
+ "13": 340,
38
+ "130": 521,
39
+ "131": 110,
40
+ "132": 240,
41
+ "133": 290,
42
+ "134": 488,
43
+ "135": 393,
44
+ "136": 302,
45
+ "137": 10,
46
+ "138": 378,
47
+ "139": 489,
48
+ "14": 428,
49
+ "140": 79,
50
+ "141": 349,
51
+ "142": 8,
52
+ "143": 61,
53
+ "144": 247,
54
+ "145": 163,
55
+ "146": 268,
56
+ "147": 55,
57
+ "148": 347,
58
+ "149": 76,
59
+ "15": 443,
60
+ "150": 499,
61
+ "151": 72,
62
+ "152": 439,
63
+ "153": 251,
64
+ "154": 361,
65
+ "155": 257,
66
+ "156": 64,
67
+ "157": 169,
68
+ "158": 265,
69
+ "159": 250,
70
+ "16": 308,
71
+ "160": 218,
72
+ "161": 450,
73
+ "162": 96,
74
+ "163": 314,
75
+ "164": 508,
76
+ "165": 516,
77
+ "166": 62,
78
+ "167": 363,
79
+ "168": 338,
80
+ "169": 90,
81
+ "17": 396,
82
+ "170": 131,
83
+ "171": 294,
84
+ "172": 350,
85
+ "173": 352,
86
+ "174": 254,
87
+ "175": 199,
88
+ "176": 179,
89
+ "177": 226,
90
+ "178": 3,
91
+ "179": 134,
92
+ "18": 239,
93
+ "180": 243,
94
+ "181": 124,
95
+ "182": 65,
96
+ "183": 284,
97
+ "184": 360,
98
+ "185": 220,
99
+ "186": 47,
100
+ "187": 432,
101
+ "188": 305,
102
+ "189": 138,
103
+ "19": 461,
104
+ "190": 200,
105
+ "191": 263,
106
+ "192": 185,
107
+ "193": 73,
108
+ "194": 22,
109
+ "195": 468,
110
+ "196": 445,
111
+ "197": 466,
112
+ "198": 66,
113
+ "199": 502,
114
+ "2": 83,
115
+ "20": 407,
116
+ "200": 319,
117
+ "201": 464,
118
+ "202": 397,
119
+ "203": 195,
120
+ "204": 452,
121
+ "205": 204,
122
+ "206": 435,
123
+ "207": 293,
124
+ "208": 470,
125
+ "209": 400,
126
+ "21": 358,
127
+ "210": 222,
128
+ "211": 513,
129
+ "212": 157,
130
+ "213": 147,
131
+ "214": 89,
132
+ "215": 525,
133
+ "216": 165,
134
+ "217": 212,
135
+ "218": 469,
136
+ "219": 43,
137
+ "22": 426,
138
+ "220": 152,
139
+ "221": 129,
140
+ "222": 295,
141
+ "223": 328,
142
+ "224": 274,
143
+ "225": 313,
144
+ "226": 529,
145
+ "227": 404,
146
+ "228": 50,
147
+ "229": 132,
148
+ "23": 209,
149
+ "230": 210,
150
+ "231": 71,
151
+ "232": 371,
152
+ "233": 171,
153
+ "234": 474,
154
+ "235": 421,
155
+ "236": 359,
156
+ "237": 326,
157
+ "238": 162,
158
+ "239": 416,
159
+ "24": 97,
160
+ "240": 515,
161
+ "241": 56,
162
+ "242": 480,
163
+ "243": 187,
164
+ "244": 411,
165
+ "245": 422,
166
+ "246": 323,
167
+ "247": 182,
168
+ "248": 98,
169
+ "249": 327,
170
+ "25": 465,
171
+ "250": 100,
172
+ "251": 409,
173
+ "252": 229,
174
+ "253": 434,
175
+ "254": 103,
176
+ "255": 130,
177
+ "256": 151,
178
+ "257": 479,
179
+ "258": 438,
180
+ "259": 276,
181
+ "26": 104,
182
+ "260": 201,
183
+ "261": 244,
184
+ "262": 387,
185
+ "263": 324,
186
+ "264": 351,
187
+ "265": 166,
188
+ "266": 92,
189
+ "267": 381,
190
+ "268": 380,
191
+ "269": 386,
192
+ "27": 447,
193
+ "270": 69,
194
+ "271": 401,
195
+ "272": 213,
196
+ "273": 148,
197
+ "274": 526,
198
+ "275": 38,
199
+ "276": 170,
200
+ "277": 376,
201
+ "278": 227,
202
+ "279": 261,
203
+ "28": 91,
204
+ "280": 287,
205
+ "281": 519,
206
+ "282": 106,
207
+ "283": 9,
208
+ "284": 427,
209
+ "285": 172,
210
+ "286": 477,
211
+ "287": 198,
212
+ "288": 430,
213
+ "289": 481,
214
+ "29": 118,
215
+ "290": 458,
216
+ "291": 80,
217
+ "292": 491,
218
+ "293": 492,
219
+ "294": 17,
220
+ "295": 419,
221
+ "296": 269,
222
+ "297": 362,
223
+ "298": 412,
224
+ "299": 343,
225
+ "3": 390,
226
+ "30": 471,
227
+ "300": 462,
228
+ "301": 153,
229
+ "302": 344,
230
+ "303": 292,
231
+ "304": 105,
232
+ "305": 158,
233
+ "306": 423,
234
+ "307": 167,
235
+ "308": 127,
236
+ "309": 140,
237
+ "31": 486,
238
+ "310": 115,
239
+ "311": 365,
240
+ "312": 456,
241
+ "313": 188,
242
+ "314": 512,
243
+ "315": 379,
244
+ "316": 177,
245
+ "317": 339,
246
+ "318": 415,
247
+ "319": 325,
248
+ "32": 123,
249
+ "320": 524,
250
+ "321": 28,
251
+ "322": 483,
252
+ "323": 37,
253
+ "324": 364,
254
+ "325": 249,
255
+ "326": 181,
256
+ "327": 219,
257
+ "328": 60,
258
+ "329": 286,
259
+ "33": 514,
260
+ "330": 33,
261
+ "331": 402,
262
+ "332": 231,
263
+ "333": 116,
264
+ "334": 316,
265
+ "335": 39,
266
+ "336": 436,
267
+ "337": 155,
268
+ "338": 460,
269
+ "339": 414,
270
+ "34": 431,
271
+ "340": 440,
272
+ "341": 406,
273
+ "342": 527,
274
+ "343": 270,
275
+ "344": 193,
276
+ "345": 211,
277
+ "346": 355,
278
+ "347": 297,
279
+ "348": 357,
280
+ "349": 77,
281
+ "35": 160,
282
+ "350": 85,
283
+ "351": 45,
284
+ "352": 417,
285
+ "353": 11,
286
+ "354": 31,
287
+ "355": 178,
288
+ "356": 478,
289
+ "357": 21,
290
+ "358": 384,
291
+ "359": 189,
292
+ "36": 36,
293
+ "360": 74,
294
+ "361": 262,
295
+ "362": 206,
296
+ "363": 99,
297
+ "364": 382,
298
+ "365": 146,
299
+ "366": 394,
300
+ "367": 518,
301
+ "368": 320,
302
+ "369": 283,
303
+ "37": 398,
304
+ "370": 154,
305
+ "371": 215,
306
+ "372": 107,
307
+ "373": 383,
308
+ "374": 78,
309
+ "375": 348,
310
+ "376": 214,
311
+ "377": 246,
312
+ "378": 53,
313
+ "379": 0,
314
+ "38": 441,
315
+ "380": 234,
316
+ "381": 40,
317
+ "382": 128,
318
+ "383": 255,
319
+ "384": 288,
320
+ "385": 111,
321
+ "386": 190,
322
+ "387": 12,
323
+ "388": 277,
324
+ "389": 4,
325
+ "39": 273,
326
+ "390": 472,
327
+ "391": 18,
328
+ "392": 453,
329
+ "393": 44,
330
+ "394": 70,
331
+ "395": 342,
332
+ "396": 117,
333
+ "397": 446,
334
+ "398": 318,
335
+ "399": 183,
336
+ "4": 32,
337
+ "40": 29,
338
+ "400": 139,
339
+ "401": 6,
340
+ "402": 498,
341
+ "403": 233,
342
+ "404": 14,
343
+ "405": 370,
344
+ "406": 196,
345
+ "407": 520,
346
+ "408": 493,
347
+ "409": 507,
348
+ "41": 95,
349
+ "410": 221,
350
+ "411": 275,
351
+ "412": 143,
352
+ "413": 25,
353
+ "414": 429,
354
+ "415": 373,
355
+ "416": 223,
356
+ "417": 87,
357
+ "418": 303,
358
+ "419": 307,
359
+ "42": 175,
360
+ "420": 252,
361
+ "421": 482,
362
+ "422": 372,
363
+ "423": 266,
364
+ "424": 285,
365
+ "425": 125,
366
+ "426": 159,
367
+ "427": 329,
368
+ "428": 180,
369
+ "429": 88,
370
+ "43": 81,
371
+ "430": 442,
372
+ "431": 304,
373
+ "432": 336,
374
+ "433": 317,
375
+ "434": 528,
376
+ "435": 126,
377
+ "436": 7,
378
+ "437": 399,
379
+ "438": 279,
380
+ "439": 5,
381
+ "44": 392,
382
+ "440": 504,
383
+ "441": 237,
384
+ "442": 500,
385
+ "443": 122,
386
+ "444": 205,
387
+ "445": 291,
388
+ "446": 264,
389
+ "447": 391,
390
+ "448": 454,
391
+ "449": 75,
392
+ "45": 473,
393
+ "450": 497,
394
+ "451": 144,
395
+ "452": 67,
396
+ "453": 345,
397
+ "454": 522,
398
+ "455": 19,
399
+ "456": 267,
400
+ "457": 101,
401
+ "458": 356,
402
+ "459": 509,
403
+ "46": 63,
404
+ "460": 322,
405
+ "461": 413,
406
+ "462": 94,
407
+ "463": 24,
408
+ "464": 194,
409
+ "465": 260,
410
+ "466": 510,
411
+ "467": 490,
412
+ "468": 192,
413
+ "469": 86,
414
+ "47": 186,
415
+ "470": 271,
416
+ "471": 225,
417
+ "472": 330,
418
+ "473": 433,
419
+ "474": 337,
420
+ "475": 511,
421
+ "476": 42,
422
+ "477": 494,
423
+ "478": 311,
424
+ "479": 476,
425
+ "48": 114,
426
+ "480": 13,
427
+ "481": 253,
428
+ "482": 15,
429
+ "483": 241,
430
+ "484": 141,
431
+ "485": 331,
432
+ "486": 306,
433
+ "487": 341,
434
+ "488": 403,
435
+ "489": 353,
436
+ "49": 455,
437
+ "490": 280,
438
+ "491": 281,
439
+ "492": 149,
440
+ "493": 208,
441
+ "494": 52,
442
+ "495": 296,
443
+ "496": 34,
444
+ "497": 108,
445
+ "498": 410,
446
+ "499": 48,
447
+ "5": 405,
448
+ "50": 230,
449
+ "500": 216,
450
+ "51": 161,
451
+ "52": 333,
452
+ "53": 346,
453
+ "54": 93,
454
+ "55": 142,
455
+ "56": 54,
456
+ "57": 354,
457
+ "58": 112,
458
+ "59": 102,
459
+ "6": 156,
460
+ "60": 133,
461
+ "61": 289,
462
+ "62": 238,
463
+ "63": 334,
464
+ "64": 135,
465
+ "65": 232,
466
+ "66": 448,
467
+ "67": 164,
468
+ "68": 395,
469
+ "69": 84,
470
+ "7": 174,
471
+ "70": 475,
472
+ "71": 49,
473
+ "72": 51,
474
+ "73": 505,
475
+ "74": 377,
476
+ "75": 389,
477
+ "76": 203,
478
+ "77": 463,
479
+ "78": 503,
480
+ "79": 248,
481
+ "8": 367,
482
+ "80": 278,
483
+ "81": 256,
484
+ "82": 310,
485
+ "83": 437,
486
+ "84": 2,
487
+ "85": 517,
488
+ "86": 168,
489
+ "87": 217,
490
+ "88": 424,
491
+ "89": 444,
492
+ "9": 523,
493
+ "90": 113,
494
+ "91": 259,
495
+ "92": 418,
496
+ "93": 136,
497
+ "94": 242,
498
+ "95": 258,
499
+ "96": 301,
500
+ "97": 300,
501
+ "98": 27,
502
+ "99": 245,
503
+ "[PAD]": 420,
504
+ "[UNK]": 1,
505
+ "a": 459,
506
+ "b": 368,
507
+ "c": 457,
508
+ "d": 68,
509
+ "e": 309,
510
+ "f": 58,
511
+ "g": 298,
512
+ "h": 191,
513
+ "i": 41,
514
+ "j": 369,
515
+ "k": 272,
516
+ "l": 150,
517
+ "m": 449,
518
+ "n": 506,
519
+ "o": 82,
520
+ "p": 197,
521
+ "q": 26,
522
+ "r": 425,
523
+ "s": 119,
524
+ "t": 228,
525
+ "u": 375,
526
+ "v": 120,
527
+ "w": 184,
528
+ "x": 487,
529
+ "y": 388,
530
+ "z": 312,
531
+ "|": 23
532
+ }