Hugging Face's logo

colorlessideas
/
xls-r-300m-cicipu-60

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
colorlessideas commited on
Commit
ddbe0b5
·
verified ·
1 Parent(s): 2fdf07b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. added_tokens.json +2 -2
  2. tokenizer_config.json +452 -5
  3. vocab.json +89 -41
added_tokens.json CHANGED
@@ -1,4 +1,4 @@
1
  {
2
- "</s>": 43,
3
- "<s>": 42
4
  }
 
1
  {
2
+ "</s>": 91,
3
+ "<s>": 90
4
  }
tokenizer_config.json CHANGED
@@ -1,6 +1,454 @@
1
  {
2
  "added_tokens_decoder": {
3
- "40": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "content": "[UNK]",
5
  "lstrip": true,
6
  "normalized": false,
@@ -8,7 +456,7 @@
8
  "single_word": false,
9
  "special": false
10
  },
11
- "41": {
12
  "content": "[PAD]",
13
  "lstrip": true,
14
  "normalized": false,
@@ -16,7 +464,7 @@
16
  "single_word": false,
17
  "special": false
18
  },
19
- "42": {
20
  "content": "<s>",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +472,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "43": {
28
  "content": "</s>",
29
  "lstrip": false,
30
  "normalized": false,
@@ -40,7 +488,6 @@
40
  "extra_special_tokens": {},
41
  "model_max_length": 1000000000000000019884624838656,
42
  "pad_token": "[PAD]",
43
- "processor_class": "Wav2Vec2Processor",
44
  "replace_word_delimiter_char": " ",
45
  "target_lang": null,
46
  "tokenizer_class": "Wav2Vec2CTCTokenizer",
 
1
  {
2
  "added_tokens_decoder": {
3
+ "1": {
4
+ "content": " ̀",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "5": {
12
+ "content": "à",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "6": {
20
+ "content": "á",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "7": {
28
+ "content": "â",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "8": {
36
+ "content": "ã̀",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "9": {
44
+ "content": "ã́",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "10": {
52
+ "content": "ã̂",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "11": {
60
+ "content": "ā",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "12": {
68
+ "content": "a̋",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "13": {
76
+ "content": "ǎ",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "18": {
84
+ "content": "è",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "19": {
92
+ "content": "é",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "20": {
100
+ "content": "ê",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "21": {
108
+ "content": "ẽ̀",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "22": {
116
+ "content": "ẽ́",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "23": {
124
+ "content": "ẽ̂",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "24": {
132
+ "content": "e̋",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "25": {
140
+ "content": "ě",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "30": {
148
+ "content": "ì",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "31": {
156
+ "content": "í",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "32": {
164
+ "content": "î",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "33": {
172
+ "content": "ĩ̀",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "34": {
180
+ "content": "ĩ́",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "35": {
188
+ "content": "ĩ̂",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "36": {
196
+ "content": "ĩ̌",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "37": {
204
+ "content": "i̋",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "38": {
212
+ "content": "ǐ",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "43": {
220
+ "content": "m̀",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "44": {
228
+ "content": "ḿ",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "46": {
236
+ "content": "ǹ",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "47": {
244
+ "content": "ń",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "49": {
252
+ "content": "ò",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "50": {
260
+ "content": "ó",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "51": {
268
+ "content": "ô",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "52": {
276
+ "content": "õ̀",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "53": {
284
+ "content": "ṍ",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "54": {
292
+ "content": "õ̂",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "55": {
300
+ "content": "ő",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "56": {
308
+ "content": "ǒ",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "62": {
316
+ "content": "ù",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "63": {
324
+ "content": "ú",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "64": {
332
+ "content": "û",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "65": {
340
+ "content": "ũ̀",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "66": {
348
+ "content": "ṹ",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "67": {
356
+ "content": "ũ̂",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "68": {
364
+ "content": "ū",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "69": {
372
+ "content": "ű",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "70": {
380
+ "content": "ǔ",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "79": {
388
+ "content": "ɔ̀",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "80": {
396
+ "content": "ɔ́",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "81": {
404
+ "content": "ɔ̂",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "82": {
412
+ "content": "ɔ̃̀",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "83": {
420
+ "content": "ɔ̃́",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "84": {
428
+ "content": "ɔ̄",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "85": {
436
+ "content": "ɔ̋",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "86": {
444
+ "content": "ɔ̌",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "88": {
452
  "content": "[UNK]",
453
  "lstrip": true,
454
  "normalized": false,
 
456
  "single_word": false,
457
  "special": false
458
  },
459
+ "89": {
460
  "content": "[PAD]",
461
  "lstrip": true,
462
  "normalized": false,
 
464
  "single_word": false,
465
  "special": false
466
  },
467
+ "90": {
468
  "content": "<s>",
469
  "lstrip": false,
470
  "normalized": false,
 
472
  "single_word": false,
473
  "special": true
474
  },
475
+ "91": {
476
  "content": "</s>",
477
  "lstrip": false,
478
  "normalized": false,
 
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",
vocab.json CHANGED
@@ -1,44 +1,92 @@
1
  {
2
- "@": 1,
3
- "[PAD]": 41,
4
- "[UNK]": 40,
5
- "a": 2,
6
- "b": 3,
7
- "c": 4,
8
- "d": 5,
9
- "e": 6,
10
- "f": 7,
11
- "g": 8,
12
- "h": 9,
13
- "i": 10,
14
- "j": 11,
15
- "k": 12,
16
- "l": 13,
17
- "m": 14,
18
- "n": 15,
19
- "o": 16,
20
- "p": 17,
21
- "r": 18,
22
- "s": 19,
23
- "t": 20,
24
- "u": 21,
25
- "v": 22,
26
- "w": 23,
27
- "x": 24,
28
- "y": 25,
29
- "z": 26,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30
  "|": 0,
31
- "ƙ": 27,
32
- "ǃ": 28,
33
- "ɓ": 29,
34
- "ɔ": 30,
35
- "ɗ": 31,
36
- "̀": 32,
37
- "́": 33,
38
- "̂": 34,
39
- "̃": 35,
40
- "̄": 36,
41
- "̋": 37,
42
- "̌": 38,
43
- "᷇": 39
44
  }
 
1
  {
2
+ " ̀": 1,
3
+ "'": 2,
4
+ "@": 3,
5
+ "[PAD]": 89,
6
+ "[UNK]": 88,
7
+ "a": 4,
8
+ "à": 5,
9
+ "á": 6,
10
+ "â": 7,
11
+ "ã̀": 8,
12
+ "ã́": 9,
13
+ "ã̂": 10,
14
+ "ā": 11,
15
+ "a̋": 12,
16
+ "ǎ": 13,
17
+ "b": 14,
18
+ "c": 15,
19
+ "d": 16,
20
+ "e": 17,
21
+ "è": 18,
22
+ "é": 19,
23
+ "ê": 20,
24
+ "ẽ̀": 21,
25
+ "ẽ́": 22,
26
+ "ẽ̂": 23,
27
+ "e̋": 24,
28
+ "ě": 25,
29
+ "f": 26,
30
+ "g": 27,
31
+ "h": 28,
32
+ "i": 29,
33
+ "ì": 30,
34
+ "í": 31,
35
+ "î": 32,
36
+ "ĩ̀": 33,
37
+ "ĩ́": 34,
38
+ "ĩ̂": 35,
39
+ "ĩ̌": 36,
40
+ "i̋": 37,
41
+ "ǐ": 38,
42
+ "j": 39,
43
+ "k": 40,
44
+ "l": 41,
45
+ "m": 42,
46
+ "m̀": 43,
47
+ "ḿ": 44,
48
+ "n": 45,
49
+ "ǹ": 46,
50
+ "ń": 47,
51
+ "o": 48,
52
+ "ò": 49,
53
+ "ó": 50,
54
+ "ô": 51,
55
+ "õ̀": 52,
56
+ "ṍ": 53,
57
+ "õ̂": 54,
58
+ "ő": 55,
59
+ "ǒ": 56,
60
+ "p": 57,
61
+ "r": 58,
62
+ "s": 59,
63
+ "t": 60,
64
+ "u": 61,
65
+ "ù": 62,
66
+ "ú": 63,
67
+ "û": 64,
68
+ "ũ̀": 65,
69
+ "ṹ": 66,
70
+ "ũ̂": 67,
71
+ "ū": 68,
72
+ "ű": 69,
73
+ "ǔ": 70,
74
+ "v": 71,
75
+ "w": 72,
76
+ "x": 73,
77
+ "y": 74,
78
+ "z": 75,
79
  "|": 0,
80
+ "ƙ": 76,
81
+ "ɓ": 77,
82
+ "ɔ": 78,
83
+ "ɔ̀": 79,
84
+ "ɔ́": 80,
85
+ "ɔ̂": 81,
86
+ "ɔ̃̀": 82,
87
+ "ɔ̃́": 83,
88
+ "ɔ̄": 84,
89
+ "ɔ̋": 85,
90
+ "ɔ̌": 86,
91
+ "ɗ": 87
 
92
  }