MagicLuke commited on
Commit
b8c0b4d
·
verified ·
1 Parent(s): 33bbc74

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "</s>": 73,
3
+ "<s>": 72,
4
+ "[PAD]": 75,
5
+ "[UNK]": 74
6
+ }
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 +1,496 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "AA0",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "AA1",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "AA2",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "AE0",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "4": {
36
+ "content": "AE1",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "AE2",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "AH0",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "AH1",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "AH2",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "AO0",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": "AO1",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "AO2",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "AW0",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "13": {
108
+ "content": "AW1",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "14": {
116
+ "content": "AW2",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "15": {
124
+ "content": "AY0",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "16": {
132
+ "content": "AY1",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "17": {
140
+ "content": "AY2",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "19": {
148
+ "content": "CH",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "21": {
156
+ "content": "DH",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "22": {
164
+ "content": "EH0",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "23": {
172
+ "content": "EH1",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "24": {
180
+ "content": "EH2",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "25": {
188
+ "content": "ER0",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "26": {
196
+ "content": "ER1",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "27": {
204
+ "content": "ER2",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "28": {
212
+ "content": "EY0",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "29": {
220
+ "content": "EY1",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "30": {
228
+ "content": "EY2",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "33": {
236
+ "content": "HH",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "34": {
244
+ "content": "IH0",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "35": {
252
+ "content": "IH1",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "36": {
260
+ "content": "IH2",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "37": {
268
+ "content": "IY0",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "38": {
276
+ "content": "IY1",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "39": {
284
+ "content": "IY2",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "40": {
292
+ "content": "JH",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "45": {
300
+ "content": "NG",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "46": {
308
+ "content": "OW0",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "47": {
316
+ "content": "OW1",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "48": {
324
+ "content": "OW2",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "49": {
332
+ "content": "OY0",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50": {
340
+ "content": "OY1",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "51": {
348
+ "content": "OY2",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "55": {
356
+ "content": "SH",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "57": {
364
+ "content": "TH",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "58": {
372
+ "content": "UH0",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "59": {
380
+ "content": "UH1",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "60": {
388
+ "content": "UH2",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "61": {
396
+ "content": "UW0",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "62": {
404
+ "content": "UW1",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "63": {
412
+ "content": "UW2",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "68": {
420
+ "content": "ZH",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "69": {
428
+ "content": "sil",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "70": {
436
+ "content": "sp",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "71": {
444
+ "content": "spn",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "72": {
452
+ "content": "<s>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "73": {
460
+ "content": "</s>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "74": {
468
+ "content": "[UNK]",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "75": {
476
+ "content": "[PAD]",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ }
483
+ },
484
+ "bos_token": "<s>",
485
+ "clean_up_tokenization_spaces": false,
486
+ "do_lower_case": false,
487
+ "eos_token": "</s>",
488
+ "extra_special_tokens": {},
489
+ "model_max_length": 1000000000000000019884624838656,
490
+ "pad_token": "[PAD]",
491
+ "replace_word_delimiter_char": " ",
492
+ "target_lang": null,
493
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
494
+ "unk_token": "[UNK]",
495
+ "word_delimiter_token": "|"
496
+ }
vocab.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "AA0": 0,
3
+ "AA1": 1,
4
+ "AA2": 2,
5
+ "AE0": 3,
6
+ "AE1": 4,
7
+ "AE2": 5,
8
+ "AH0": 6,
9
+ "AH1": 7,
10
+ "AH2": 8,
11
+ "AO0": 9,
12
+ "AO1": 10,
13
+ "AO2": 11,
14
+ "AW0": 12,
15
+ "AW1": 13,
16
+ "AW2": 14,
17
+ "AY0": 15,
18
+ "AY1": 16,
19
+ "AY2": 17,
20
+ "B": 18,
21
+ "CH": 19,
22
+ "D": 20,
23
+ "DH": 21,
24
+ "EH0": 22,
25
+ "EH1": 23,
26
+ "EH2": 24,
27
+ "ER0": 25,
28
+ "ER1": 26,
29
+ "ER2": 27,
30
+ "EY0": 28,
31
+ "EY1": 29,
32
+ "EY2": 30,
33
+ "F": 31,
34
+ "G": 32,
35
+ "HH": 33,
36
+ "IH0": 34,
37
+ "IH1": 35,
38
+ "IH2": 36,
39
+ "IY0": 37,
40
+ "IY1": 38,
41
+ "IY2": 39,
42
+ "JH": 40,
43
+ "K": 41,
44
+ "L": 42,
45
+ "M": 43,
46
+ "N": 44,
47
+ "NG": 45,
48
+ "OW0": 46,
49
+ "OW1": 47,
50
+ "OW2": 48,
51
+ "OY0": 49,
52
+ "OY1": 50,
53
+ "OY2": 51,
54
+ "P": 52,
55
+ "R": 53,
56
+ "S": 54,
57
+ "SH": 55,
58
+ "T": 56,
59
+ "TH": 57,
60
+ "UH0": 58,
61
+ "UH1": 59,
62
+ "UH2": 60,
63
+ "UW0": 61,
64
+ "UW1": 62,
65
+ "UW2": 63,
66
+ "V": 64,
67
+ "W": 65,
68
+ "Y": 66,
69
+ "Z": 67,
70
+ "ZH": 68,
71
+ "sil": 69,
72
+ "sp": 70,
73
+ "spn": 71
74
+ }