truong-xuan-linh commited on
Commit
c382647
1 Parent(s): c9de121

Upload processor

Browse files
added_tokens.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79,
4
+ "ch": 146,
5
+ "gh": 147,
6
+ "gi": 155,
7
+ "kh": 148,
8
+ "ng": 149,
9
+ "ngh": 150,
10
+ "nh": 151,
11
+ "ph": 152,
12
+ "qu": 156,
13
+ "th": 153,
14
+ "tr": 154,
15
+ "à": 114,
16
+ "á": 103,
17
+ "â": 108,
18
+ "ã": 113,
19
+ "è": 87,
20
+ "ì": 128,
21
+ "í": 131,
22
+ "ò": 145,
23
+ "ó": 121,
24
+ "ô": 96,
25
+ "õ": 132,
26
+ "ù": 104,
27
+ "ú": 129,
28
+ "ý": 84,
29
+ "ă": 116,
30
+ "đ": 123,
31
+ "ĩ": 117,
32
+ "ũ": 88,
33
+ "ơ": 100,
34
+ "ư": 97,
35
+ "ạ": 109,
36
+ "ả": 136,
37
+ "ấ": 112,
38
+ "ầ": 127,
39
+ "ẩ": 107,
40
+ "ẫ": 122,
41
+ "ậ": 143,
42
+ "ắ": 111,
43
+ "ằ": 118,
44
+ "ẳ": 119,
45
+ "ẵ": 86,
46
+ "ặ": 81,
47
+ "ẹ": 95,
48
+ "ẻ": 139,
49
+ "ẽ": 124,
50
+ "ế": 144,
51
+ "ề": 99,
52
+ "ể": 90,
53
+ "ễ": 120,
54
+ "ệ": 98,
55
+ "ỉ": 82,
56
+ "ị": 94,
57
+ "ọ": 115,
58
+ "ỏ": 140,
59
+ "ố": 106,
60
+ "ồ": 89,
61
+ "ổ": 83,
62
+ "ỗ": 91,
63
+ "ộ": 134,
64
+ "ớ": 130,
65
+ "ờ": 85,
66
+ "ở": 126,
67
+ "ỡ": 141,
68
+ "ợ": 110,
69
+ "ụ": 142,
70
+ "ủ": 92,
71
+ "ứ": 105,
72
+ "ừ": 125,
73
+ "ử": 135,
74
+ "ữ": 102,
75
+ "ự": 137,
76
+ "ỳ": 138,
77
+ "ỵ": 133,
78
+ "ỷ": 101,
79
+ "ỹ": 93
80
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": false,
3
+ "feature_extractor_type": "SpeechT5FeatureExtractor",
4
+ "feature_size": 1,
5
+ "fmax": 7600,
6
+ "fmin": 80,
7
+ "frame_signal_scale": 1.0,
8
+ "hop_length": 16,
9
+ "mel_floor": 1e-10,
10
+ "num_mel_bins": 80,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "processor_class": "SpeechT5Processor",
14
+ "reduction_factor": 2,
15
+ "return_attention_mask": true,
16
+ "sampling_rate": 16000,
17
+ "win_function": "hann_window",
18
+ "win_length": 64
19
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": true,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
spm_char.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcc48f3e225f627b1641db410ceb0c8649bd2b0c982e150b03f8be3728ab560
3
+ size 238473
tokenizer_config.json ADDED
@@ -0,0 +1,1271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "▁",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "e",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "t",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "a",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "o",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "n",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": "i",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "h",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "s",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "13": {
108
+ "content": "r",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "14": {
116
+ "content": "d",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "15": {
124
+ "content": "l",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "16": {
132
+ "content": "u",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "17": {
140
+ "content": "c",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "18": {
148
+ "content": "m",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "19": {
156
+ "content": "f",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "20": {
164
+ "content": "w",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "21": {
172
+ "content": "g",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "22": {
180
+ "content": "y",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "23": {
188
+ "content": ",",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "24": {
196
+ "content": "p",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "25": {
204
+ "content": "b",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "26": {
212
+ "content": ".",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "27": {
220
+ "content": "v",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "28": {
228
+ "content": "k",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "29": {
236
+ "content": "\"",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "30": {
244
+ "content": "I",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "31": {
252
+ "content": "'",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "32": {
260
+ "content": "T",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "33": {
268
+ "content": "A",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "34": {
276
+ "content": "S",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "35": {
284
+ "content": "H",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "36": {
292
+ "content": ";",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "37": {
300
+ "content": "x",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "38": {
308
+ "content": "W",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "39": {
316
+ "content": "-",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "40": {
324
+ "content": "B",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "41": {
332
+ "content": "?",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "42": {
340
+ "content": "C",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "43": {
348
+ "content": "M",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "44": {
356
+ "content": "!",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "45": {
364
+ "content": "q",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "46": {
372
+ "content": "j",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "47": {
380
+ "content": "E",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "48": {
388
+ "content": "N",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "49": {
396
+ "content": "P",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50": {
404
+ "content": "O",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "51": {
412
+ "content": "D",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "52": {
420
+ "content": "L",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "53": {
428
+ "content": "G",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "54": {
436
+ "content": "R",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "55": {
444
+ "content": "F",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "56": {
452
+ "content": "Y",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "57": {
460
+ "content": "z",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "58": {
468
+ "content": "J",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "59": {
476
+ "content": ":",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "60": {
484
+ "content": "K",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "61": {
492
+ "content": "U",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "62": {
500
+ "content": "V",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "63": {
508
+ "content": ")",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "64": {
516
+ "content": "(",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "65": {
524
+ "content": "Q",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "66": {
532
+ "content": "Z",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "67": {
540
+ "content": "]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "68": {
548
+ "content": "[",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "69": {
556
+ "content": "X",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "70": {
564
+ "content": "—",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "71": {
572
+ "content": "/",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "72": {
580
+ "content": "æ",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "73": {
588
+ "content": "é",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "74": {
596
+ "content": "{",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "75": {
604
+ "content": "}",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "76": {
612
+ "content": "ê",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "77": {
620
+ "content": "œ",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "78": {
628
+ "content": "̄",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "79": {
636
+ "content": "<mask>",
637
+ "lstrip": true,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "80": {
644
+ "content": "<ctc_blank>",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "81": {
652
+ "content": "ặ",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "82": {
660
+ "content": "ỉ",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "83": {
668
+ "content": "ổ",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "84": {
676
+ "content": "ý",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "85": {
684
+ "content": "ờ",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "86": {
692
+ "content": "ẵ",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "87": {
700
+ "content": "è",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "88": {
708
+ "content": "ũ",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "89": {
716
+ "content": "ồ",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "90": {
724
+ "content": "ể",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "91": {
732
+ "content": "ỗ",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "92": {
740
+ "content": "ủ",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "93": {
748
+ "content": "ỹ",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "94": {
756
+ "content": "ị",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95": {
764
+ "content": "ẹ",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "96": {
772
+ "content": "ô",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "97": {
780
+ "content": "ư",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "98": {
788
+ "content": "ệ",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "99": {
796
+ "content": "ề",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "100": {
804
+ "content": "ơ",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "101": {
812
+ "content": "ỷ",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "102": {
820
+ "content": "ữ",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "103": {
828
+ "content": "á",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "104": {
836
+ "content": "ù",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "105": {
844
+ "content": "ứ",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "106": {
852
+ "content": "ố",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "107": {
860
+ "content": "ẩ",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "108": {
868
+ "content": "â",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "109": {
876
+ "content": "ạ",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "110": {
884
+ "content": "ợ",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "111": {
892
+ "content": "ắ",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "112": {
900
+ "content": "ấ",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "113": {
908
+ "content": "ã",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "114": {
916
+ "content": "à",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "115": {
924
+ "content": "ọ",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ },
931
+ "116": {
932
+ "content": "ă",
933
+ "lstrip": false,
934
+ "normalized": true,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": false
938
+ },
939
+ "117": {
940
+ "content": "ĩ",
941
+ "lstrip": false,
942
+ "normalized": true,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": false
946
+ },
947
+ "118": {
948
+ "content": "ằ",
949
+ "lstrip": false,
950
+ "normalized": true,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": false
954
+ },
955
+ "119": {
956
+ "content": "ẳ",
957
+ "lstrip": false,
958
+ "normalized": true,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": false
962
+ },
963
+ "120": {
964
+ "content": "ễ",
965
+ "lstrip": false,
966
+ "normalized": true,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": false
970
+ },
971
+ "121": {
972
+ "content": "ó",
973
+ "lstrip": false,
974
+ "normalized": true,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": false
978
+ },
979
+ "122": {
980
+ "content": "ẫ",
981
+ "lstrip": false,
982
+ "normalized": true,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": false
986
+ },
987
+ "123": {
988
+ "content": "đ",
989
+ "lstrip": false,
990
+ "normalized": true,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": false
994
+ },
995
+ "124": {
996
+ "content": "ẽ",
997
+ "lstrip": false,
998
+ "normalized": true,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": false
1002
+ },
1003
+ "125": {
1004
+ "content": "ừ",
1005
+ "lstrip": false,
1006
+ "normalized": true,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": false
1010
+ },
1011
+ "126": {
1012
+ "content": "ở",
1013
+ "lstrip": false,
1014
+ "normalized": true,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": false
1018
+ },
1019
+ "127": {
1020
+ "content": "ầ",
1021
+ "lstrip": false,
1022
+ "normalized": true,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": false
1026
+ },
1027
+ "128": {
1028
+ "content": "ì",
1029
+ "lstrip": false,
1030
+ "normalized": true,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": false
1034
+ },
1035
+ "129": {
1036
+ "content": "ú",
1037
+ "lstrip": false,
1038
+ "normalized": true,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": false
1042
+ },
1043
+ "130": {
1044
+ "content": "ớ",
1045
+ "lstrip": false,
1046
+ "normalized": true,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": false
1050
+ },
1051
+ "131": {
1052
+ "content": "í",
1053
+ "lstrip": false,
1054
+ "normalized": true,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": false
1058
+ },
1059
+ "132": {
1060
+ "content": "õ",
1061
+ "lstrip": false,
1062
+ "normalized": true,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": false
1066
+ },
1067
+ "133": {
1068
+ "content": "ỵ",
1069
+ "lstrip": false,
1070
+ "normalized": true,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": false
1074
+ },
1075
+ "134": {
1076
+ "content": "ộ",
1077
+ "lstrip": false,
1078
+ "normalized": true,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": false
1082
+ },
1083
+ "135": {
1084
+ "content": "ử",
1085
+ "lstrip": false,
1086
+ "normalized": true,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": false
1090
+ },
1091
+ "136": {
1092
+ "content": "ả",
1093
+ "lstrip": false,
1094
+ "normalized": true,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": false
1098
+ },
1099
+ "137": {
1100
+ "content": "ự",
1101
+ "lstrip": false,
1102
+ "normalized": true,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": false
1106
+ },
1107
+ "138": {
1108
+ "content": "ỳ",
1109
+ "lstrip": false,
1110
+ "normalized": true,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": false
1114
+ },
1115
+ "139": {
1116
+ "content": "ẻ",
1117
+ "lstrip": false,
1118
+ "normalized": true,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": false
1122
+ },
1123
+ "140": {
1124
+ "content": "ỏ",
1125
+ "lstrip": false,
1126
+ "normalized": true,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": false
1130
+ },
1131
+ "141": {
1132
+ "content": "ỡ",
1133
+ "lstrip": false,
1134
+ "normalized": true,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": false
1138
+ },
1139
+ "142": {
1140
+ "content": "ụ",
1141
+ "lstrip": false,
1142
+ "normalized": true,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": false
1146
+ },
1147
+ "143": {
1148
+ "content": "ậ",
1149
+ "lstrip": false,
1150
+ "normalized": true,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": false
1154
+ },
1155
+ "144": {
1156
+ "content": "ế",
1157
+ "lstrip": false,
1158
+ "normalized": true,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": false
1162
+ },
1163
+ "145": {
1164
+ "content": "ò",
1165
+ "lstrip": false,
1166
+ "normalized": true,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": false
1170
+ },
1171
+ "146": {
1172
+ "content": "ch",
1173
+ "lstrip": false,
1174
+ "normalized": true,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": false
1178
+ },
1179
+ "147": {
1180
+ "content": "gh",
1181
+ "lstrip": false,
1182
+ "normalized": true,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": false
1186
+ },
1187
+ "148": {
1188
+ "content": "kh",
1189
+ "lstrip": false,
1190
+ "normalized": true,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": false
1194
+ },
1195
+ "149": {
1196
+ "content": "ng",
1197
+ "lstrip": false,
1198
+ "normalized": true,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": false
1202
+ },
1203
+ "150": {
1204
+ "content": "ngh",
1205
+ "lstrip": false,
1206
+ "normalized": true,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": false
1210
+ },
1211
+ "151": {
1212
+ "content": "nh",
1213
+ "lstrip": false,
1214
+ "normalized": true,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": false
1218
+ },
1219
+ "152": {
1220
+ "content": "ph",
1221
+ "lstrip": false,
1222
+ "normalized": true,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": false
1226
+ },
1227
+ "153": {
1228
+ "content": "th",
1229
+ "lstrip": false,
1230
+ "normalized": true,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": false
1234
+ },
1235
+ "154": {
1236
+ "content": "tr",
1237
+ "lstrip": false,
1238
+ "normalized": true,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": false
1242
+ },
1243
+ "155": {
1244
+ "content": "gi",
1245
+ "lstrip": false,
1246
+ "normalized": true,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": false
1250
+ },
1251
+ "156": {
1252
+ "content": "qu",
1253
+ "lstrip": false,
1254
+ "normalized": true,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": false
1258
+ }
1259
+ },
1260
+ "bos_token": "<s>",
1261
+ "clean_up_tokenization_spaces": true,
1262
+ "eos_token": "</s>",
1263
+ "mask_token": "<mask>",
1264
+ "model_max_length": 600,
1265
+ "normalize": false,
1266
+ "pad_token": "<pad>",
1267
+ "processor_class": "SpeechT5Processor",
1268
+ "sp_model_kwargs": {},
1269
+ "tokenizer_class": "SpeechT5Tokenizer",
1270
+ "unk_token": "<unk>"
1271
+ }