Hugging Face's logo

hon9kon9ize
/
wav2vec2bert-jyutping

Safetensors
wav2vec2-bert
Model card Files Community
indiejoseph commited on
Commit
f923cfc
•
1 Parent(s): e931baf

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. added_tokens.json +4 -0
  2. config.json +82 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +11 -0
  5. special_tokens_map.json +6 -0
  6. tokenizer_config.json +680 -0
  7. vocab.json +83 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 82,
3
+ "<s>": 81
4
+ }
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/w2v-bert-2.0",
3
+ "activation_dropout": 0.0,
4
+ "adapter_act": "relu",
5
+ "adapter_kernel_size": 3,
6
+ "adapter_stride": 2,
7
+ "add_adapter": true,
8
+ "apply_spec_augment": false,
9
+ "architectures": [
10
+ "Wav2Vec2BertForCTC"
11
+ ],
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 1,
14
+ "classifier_proj_size": 768,
15
+ "codevector_dim": 768,
16
+ "conformer_conv_dropout": 0.1,
17
+ "contrastive_logits_temperature": 0.1,
18
+ "conv_depthwise_kernel_size": 31,
19
+ "ctc_loss_reduction": "mean",
20
+ "ctc_zero_infinity": false,
21
+ "diversity_loss_weight": 0.1,
22
+ "eos_token_id": 2,
23
+ "feat_proj_dropout": 0.0,
24
+ "feat_quantizer_dropout": 0.0,
25
+ "feature_projection_input_dim": 160,
26
+ "final_dropout": 0.1,
27
+ "hidden_act": "swish",
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 1024,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "layer_norm_eps": 1e-05,
33
+ "layerdrop": 0.0,
34
+ "left_max_position_embeddings": 64,
35
+ "mask_feature_length": 10,
36
+ "mask_feature_min_masks": 0,
37
+ "mask_feature_prob": 0.0,
38
+ "mask_time_length": 10,
39
+ "mask_time_min_masks": 2,
40
+ "mask_time_prob": 0.0,
41
+ "max_source_positions": 5000,
42
+ "model_type": "wav2vec2-bert",
43
+ "num_adapter_layers": 1,
44
+ "num_attention_heads": 16,
45
+ "num_codevector_groups": 2,
46
+ "num_codevectors_per_group": 320,
47
+ "num_hidden_layers": 24,
48
+ "num_negatives": 100,
49
+ "output_hidden_size": 1024,
50
+ "pad_token_id": 0,
51
+ "position_embeddings_type": "relative_key",
52
+ "proj_codevector_dim": 768,
53
+ "right_max_position_embeddings": 8,
54
+ "rotary_embedding_base": 10000,
55
+ "tdnn_dilation": [
56
+ 1,
57
+ 2,
58
+ 3,
59
+ 1,
60
+ 1
61
+ ],
62
+ "tdnn_dim": [
63
+ 512,
64
+ 512,
65
+ 512,
66
+ 512,
67
+ 1500
68
+ ],
69
+ "tdnn_kernel": [
70
+ 5,
71
+ 3,
72
+ 3,
73
+ 1,
74
+ 1
75
+ ],
76
+ "torch_dtype": "float32",
77
+ "transformers_version": "4.39.3",
78
+ "use_intermediate_ffn_before_adapter": false,
79
+ "use_weighted_layer_sum": false,
80
+ "vocab_size": 83,
81
+ "xvector_output_dim": 512
82
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c18469221b41744812126ceae2a2f29a390789676cbcdd9b89afa9fd79387f3
3
+ size 2423154860
preprocessor_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor_type": "SeamlessM4TFeatureExtractor",
3
+ "feature_size": 80,
4
+ "num_mel_bins": 80,
5
+ "padding_side": "right",
6
+ "padding_value": 1,
7
+ "processor_class": "Wav2Vec2BertProcessor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000,
10
+ "stride": 2
11
+ }
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 +1,680 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "2": {
20
+ "content": "|",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "3": {
28
+ "content": "1",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "4": {
36
+ "content": "2",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "3",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "4",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "5",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "6",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "M",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": "Ng",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "aa",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "aai",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "13": {
108
+ "content": "aak",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "14": {
116
+ "content": "aam",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "15": {
124
+ "content": "aan",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "16": {
132
+ "content": "aang",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "17": {
140
+ "content": "aap",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "18": {
148
+ "content": "aat",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "19": {
156
+ "content": "aau",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "20": {
164
+ "content": "ai",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "21": {
172
+ "content": "ak",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "22": {
180
+ "content": "am",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "23": {
188
+ "content": "an",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "24": {
196
+ "content": "ang",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "25": {
204
+ "content": "ap",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "26": {
212
+ "content": "at",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "27": {
220
+ "content": "au",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "28": {
228
+ "content": "b",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "29": {
236
+ "content": "c",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "30": {
244
+ "content": "d",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "31": {
252
+ "content": "e",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "32": {
260
+ "content": "ei",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "33": {
268
+ "content": "ek",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "34": {
276
+ "content": "eng",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "35": {
284
+ "content": "eoi",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "36": {
292
+ "content": "eon",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "37": {
300
+ "content": "eot",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "38": {
308
+ "content": "f",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "39": {
316
+ "content": "g",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "40": {
324
+ "content": "gw",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "41": {
332
+ "content": "h",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "42": {
340
+ "content": "i",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "43": {
348
+ "content": "ik",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "44": {
356
+ "content": "im",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "45": {
364
+ "content": "in",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "46": {
372
+ "content": "ing",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "47": {
380
+ "content": "ip",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "48": {
388
+ "content": "it",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "49": {
396
+ "content": "iu",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50": {
404
+ "content": "j",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "51": {
412
+ "content": "k",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "52": {
420
+ "content": "kw",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "53": {
428
+ "content": "l",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "54": {
436
+ "content": "m",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "55": {
444
+ "content": "n",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "56": {
452
+ "content": "ng",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "57": {
460
+ "content": "o",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "58": {
468
+ "content": "oe",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "59": {
476
+ "content": "oek",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "60": {
484
+ "content": "oeng",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "61": {
492
+ "content": "oi",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "62": {
500
+ "content": "ok",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "63": {
508
+ "content": "on",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "64": {
516
+ "content": "ong",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "65": {
524
+ "content": "ot",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "66": {
532
+ "content": "ou",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "67": {
540
+ "content": "p",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "68": {
548
+ "content": "s",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "69": {
556
+ "content": "t",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "70": {
564
+ "content": "u",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "71": {
572
+ "content": "ui",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "72": {
580
+ "content": "uk",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "73": {
588
+ "content": "un",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "74": {
596
+ "content": "ung",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "75": {
604
+ "content": "ut",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "76": {
612
+ "content": "w",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "77": {
620
+ "content": "yu",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "78": {
628
+ "content": "yun",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "79": {
636
+ "content": "yut",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "80": {
644
+ "content": "z",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "81": {
652
+ "content": "<s>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "82": {
660
+ "content": "</s>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ }
667
+ },
668
+ "bos_token": "<s>",
669
+ "clean_up_tokenization_spaces": true,
670
+ "do_lower_case": false,
671
+ "eos_token": "</s>",
672
+ "model_max_length": 1000000000000000019884624838656,
673
+ "pad_token": "[PAD]",
674
+ "processor_class": "Wav2Vec2BertProcessor",
675
+ "replace_word_delimiter_char": " ",
676
+ "target_lang": null,
677
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
678
+ "unk_token": "[UNK]",
679
+ "word_delimiter_token": "|"
680
+ }
vocab.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "1": 3,
3
+ "2": 4,
4
+ "3": 5,
5
+ "4": 6,
6
+ "5": 7,
7
+ "6": 8,
8
+ "M": 9,
9
+ "Ng": 10,
10
+ "[PAD]": 0,
11
+ "[UNK]": 1,
12
+ "aa": 11,
13
+ "aai": 12,
14
+ "aak": 13,
15
+ "aam": 14,
16
+ "aan": 15,
17
+ "aang": 16,
18
+ "aap": 17,
19
+ "aat": 18,
20
+ "aau": 19,
21
+ "ai": 20,
22
+ "ak": 21,
23
+ "am": 22,
24
+ "an": 23,
25
+ "ang": 24,
26
+ "ap": 25,
27
+ "at": 26,
28
+ "au": 27,
29
+ "b": 28,
30
+ "c": 29,
31
+ "d": 30,
32
+ "e": 31,
33
+ "ei": 32,
34
+ "ek": 33,
35
+ "eng": 34,
36
+ "eoi": 35,
37
+ "eon": 36,
38
+ "eot": 37,
39
+ "f": 38,
40
+ "g": 39,
41
+ "gw": 40,
42
+ "h": 41,
43
+ "i": 42,
44
+ "ik": 43,
45
+ "im": 44,
46
+ "in": 45,
47
+ "ing": 46,
48
+ "ip": 47,
49
+ "it": 48,
50
+ "iu": 49,
51
+ "j": 50,
52
+ "k": 51,
53
+ "kw": 52,
54
+ "l": 53,
55
+ "m": 54,
56
+ "n": 55,
57
+ "ng": 56,
58
+ "o": 57,
59
+ "oe": 58,
60
+ "oek": 59,
61
+ "oeng": 60,
62
+ "oi": 61,
63
+ "ok": 62,
64
+ "on": 63,
65
+ "ong": 64,
66
+ "ot": 65,
67
+ "ou": 66,
68
+ "p": 67,
69
+ "s": 68,
70
+ "t": 69,
71
+ "u": 70,
72
+ "ui": 71,
73
+ "uk": 72,
74
+ "un": 73,
75
+ "ung": 74,
76
+ "ut": 75,
77
+ "w": 76,
78
+ "yu": 77,
79
+ "yun": 78,
80
+ "yut": 79,
81
+ "z": 80,
82
+ "|": 2
83
+ }