Hugging Face's logo

badrex
/
Ethio-ASR-multilingual-600M

Automatic Speech Recognition
Transformers
Safetensors
Amharic
Tigrinya
Oromo
wav2vec2-bert
multilingual
Model card Files
xet
 Community
badrex commited on
Commit
867db8a
·
verified ·
1 Parent(s): 5f2b377

Upload processor

Browse files
Files changed (5) hide show
  1. added_tokens.json +4 -0
  2. preprocessor_config.json +11 -0
  3. special_tokens_map.json +30 -0
  4. tokenizer_config.json +89 -0
  5. vocab.json +416 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 415,
3
+ "<s>": 414
4
+ }
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": true,
19
+ "normalized": false,
20
+ "rstrip": true,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "[UNK]",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "407": {
4
+ "content": "[UNK]",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "408": {
12
+ "content": "[PAD]",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "409": {
20
+ "content": "[TIR]",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "410": {
28
+ "content": "[WAL]",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "411": {
36
+ "content": "[AMH]",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "412": {
44
+ "content": "[SID]",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "413": {
52
+ "content": "[ORM]",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "414": {
60
+ "content": "<s>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "415": {
68
+ "content": "</s>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ }
75
+ },
76
+ "bos_token": "<s>",
77
+ "clean_up_tokenization_spaces": false,
78
+ "do_lower_case": false,
79
+ "eos_token": "</s>",
80
+ "extra_special_tokens": {},
81
+ "model_max_length": 1000000000000000019884624838656,
82
+ "pad_token": "[PAD]",
83
+ "processor_class": "Wav2Vec2BertProcessor",
84
+ "replace_word_delimiter_char": " ",
85
+ "target_lang": null,
86
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
87
+ "unk_token": "[UNK]",
88
+ "word_delimiter_token": "|"
89
+ }
vocab.json ADDED
@@ -0,0 +1,416 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "!": 1,
3
+ "#": 2,
4
+ "$": 3,
5
+ "%": 4,
6
+ "&": 5,
7
+ "'": 6,
8
+ "*": 7,
9
+ "+": 8,
10
+ ",": 9,
11
+ "-": 10,
12
+ ".": 11,
13
+ "0": 12,
14
+ "1": 13,
15
+ "2": 14,
16
+ "3": 15,
17
+ "4": 16,
18
+ "5": 17,
19
+ "6": 18,
20
+ "7": 19,
21
+ "8": 20,
22
+ "9": 21,
23
+ "=": 22,
24
+ "?": 23,
25
+ "@": 24,
26
+ "[AMH]": 411,
27
+ "[ORM]": 413,
28
+ "[PAD]": 408,
29
+ "[SID]": 412,
30
+ "[TIR]": 409,
31
+ "[UNK]": 407,
32
+ "[WAL]": 410,
33
+ "a": 25,
34
+ "b": 26,
35
+ "c": 27,
36
+ "d": 28,
37
+ "e": 29,
38
+ "f": 30,
39
+ "g": 31,
40
+ "h": 32,
41
+ "i": 33,
42
+ "j": 34,
43
+ "k": 35,
44
+ "l": 36,
45
+ "m": 37,
46
+ "n": 38,
47
+ "o": 39,
48
+ "p": 40,
49
+ "q": 41,
50
+ "r": 42,
51
+ "s": 43,
52
+ "t": 44,
53
+ "u": 45,
54
+ "v": 46,
55
+ "w": 47,
56
+ "x": 48,
57
+ "y": 49,
58
+ "z": 50,
59
+ "|": 0,
60
+ "ሀ": 51,
61
+ "ሁ": 52,
62
+ "ሂ": 53,
63
+ "ሃ": 54,
64
+ "ሄ": 55,
65
+ "ህ": 56,
66
+ "ሆ": 57,
67
+ "ሇ": 58,
68
+ "ለ": 59,
69
+ "ሉ": 60,
70
+ "ሊ": 61,
71
+ "ላ": 62,
72
+ "ሌ": 63,
73
+ "ል": 64,
74
+ "ሎ": 65,
75
+ "ሏ": 66,
76
+ "ሐ": 67,
77
+ "ሑ": 68,
78
+ "ሒ": 69,
79
+ "ሓ": 70,
80
+ "ሔ": 71,
81
+ "ሕ": 72,
82
+ "ሖ": 73,
83
+ "ሗ": 74,
84
+ "መ": 75,
85
+ "ሙ": 76,
86
+ "ሚ": 77,
87
+ "ማ": 78,
88
+ "ሜ": 79,
89
+ "ም": 80,
90
+ "ሞ": 81,
91
+ "ሟ": 82,
92
+ "ሠ": 83,
93
+ "ሡ": 84,
94
+ "ሢ": 85,
95
+ "ሣ": 86,
96
+ "ሤ": 87,
97
+ "ሥ": 88,
98
+ "ሦ": 89,
99
+ "ሧ": 90,
100
+ "ረ": 91,
101
+ "ሩ": 92,
102
+ "ሪ": 93,
103
+ "ራ": 94,
104
+ "ሬ": 95,
105
+ "ር": 96,
106
+ "ሮ": 97,
107
+ "ሯ": 98,
108
+ "ሰ": 99,
109
+ "ሱ": 100,
110
+ "ሲ": 101,
111
+ "ሳ": 102,
112
+ "ሴ": 103,
113
+ "ስ": 104,
114
+ "ሶ": 105,
115
+ "ሷ": 106,
116
+ "ሸ": 107,
117
+ "ሹ": 108,
118
+ "ሺ": 109,
119
+ "ሻ": 110,
120
+ "ሼ": 111,
121
+ "ሽ": 112,
122
+ "ሾ": 113,
123
+ "ሿ": 114,
124
+ "ቀ": 115,
125
+ "ቁ": 116,
126
+ "ቂ": 117,
127
+ "ቃ": 118,
128
+ "ቄ": 119,
129
+ "ቅ": 120,
130
+ "ቆ": 121,
131
+ "ቇ": 122,
132
+ "ቈ": 123,
133
+ "ቊ": 124,
134
+ "ቋ": 125,
135
+ "ቌ": 126,
136
+ "ቍ": 127,
137
+ "ቐ": 128,
138
+ "ቑ": 129,
139
+ "ቒ": 130,
140
+ "ቓ": 131,
141
+ "ቔ": 132,
142
+ "ቕ": 133,
143
+ "ቖ": 134,
144
+ "ቘ": 135,
145
+ "ቚ": 136,
146
+ "ቛ": 137,
147
+ "ቜ": 138,
148
+ "ቝ": 139,
149
+ "በ": 140,
150
+ "ቡ": 141,
151
+ "ቢ": 142,
152
+ "ባ": 143,
153
+ "ቤ": 144,
154
+ "ብ": 145,
155
+ "ቦ": 146,
156
+ "ቧ": 147,
157
+ "ቨ": 148,
158
+ "ቩ": 149,
159
+ "ቪ": 150,
160
+ "ቫ": 151,
161
+ "ቬ": 152,
162
+ "ቭ": 153,
163
+ "ቮ": 154,
164
+ "ቯ": 155,
165
+ "ተ": 156,
166
+ "ቱ": 157,
167
+ "ቲ": 158,
168
+ "ታ": 159,
169
+ "ቴ": 160,
170
+ "ት": 161,
171
+ "ቶ": 162,
172
+ "ቷ": 163,
173
+ "ቸ": 164,
174
+ "ቹ": 165,
175
+ "ቺ": 166,
176
+ "ቻ": 167,
177
+ "ቼ": 168,
178
+ "ች": 169,
179
+ "ቾ": 170,
180
+ "ቿ": 171,
181
+ "ኀ": 172,
182
+ "ኁ": 173,
183
+ "ኂ": 174,
184
+ "ኃ": 175,
185
+ "ኄ": 176,
186
+ "ኅ": 177,
187
+ "ኆ": 178,
188
+ "ኇ": 179,
189
+ "ኈ": 180,
190
+ "ኊ": 181,
191
+ "ኋ": 182,
192
+ "ኌ": 183,
193
+ "ኍ": 184,
194
+ "ነ": 185,
195
+ "ኑ": 186,
196
+ "ኒ": 187,
197
+ "ና": 188,
198
+ "ኔ": 189,
199
+ "ን": 190,
200
+ "ኖ": 191,
201
+ "ኗ": 192,
202
+ "ኘ": 193,
203
+ "ኙ": 194,
204
+ "ኚ": 195,
205
+ "ኛ": 196,
206
+ "ኜ": 197,
207
+ "ኝ": 198,
208
+ "ኞ": 199,
209
+ "ኟ": 200,
210
+ "አ": 201,
211
+ "ኡ": 202,
212
+ "ኢ": 203,
213
+ "ኣ": 204,
214
+ "ኤ": 205,
215
+ "እ": 206,
216
+ "ኦ": 207,
217
+ "ኧ": 208,
218
+ "ከ": 209,
219
+ "ኩ": 210,
220
+ "ኪ": 211,
221
+ "ካ": 212,
222
+ "ኬ": 213,
223
+ "ክ": 214,
224
+ "ኮ": 215,
225
+ "ኯ": 216,
226
+ "ኰ": 217,
227
+ "ኲ": 218,
228
+ "ኳ": 219,
229
+ "ኴ": 220,
230
+ "ኵ": 221,
231
+ "ኸ": 222,
232
+ "ኹ": 223,
233
+ "ኺ": 224,
234
+ "ኻ": 225,
235
+ "ኼ": 226,
236
+ "ኽ": 227,
237
+ "ኾ": 228,
238
+ "ዀ": 229,
239
+ "ዂ": 230,
240
+ "ዃ": 231,
241
+ "ዄ": 232,
242
+ "ዅ": 233,
243
+ "ወ": 234,
244
+ "ዉ": 235,
245
+ "ዊ": 236,
246
+ "ዋ": 237,
247
+ "ዌ": 238,
248
+ "ው": 239,
249
+ "ዎ": 240,
250
+ "ዏ": 241,
251
+ "ዐ": 242,
252
+ "ዑ": 243,
253
+ "ዒ": 244,
254
+ "ዓ": 245,
255
+ "ዔ": 246,
256
+ "ዕ": 247,
257
+ "ዖ": 248,
258
+ "ዘ": 249,
259
+ "ዙ": 250,
260
+ "ዚ": 251,
261
+ "ዛ": 252,
262
+ "ዜ": 253,
263
+ "ዝ": 254,
264
+ "ዞ": 255,
265
+ "ዟ": 256,
266
+ "ዠ": 257,
267
+ "ዡ": 258,
268
+ "ዢ": 259,
269
+ "ዣ": 260,
270
+ "ዤ": 261,
271
+ "ዥ": 262,
272
+ "ዦ": 263,
273
+ "ዧ": 264,
274
+ "የ": 265,
275
+ "ዩ": 266,
276
+ "ዪ": 267,
277
+ "ያ": 268,
278
+ "ዬ": 269,
279
+ "ይ": 270,
280
+ "ዮ": 271,
281
+ "ዯ": 272,
282
+ "ደ": 273,
283
+ "ዱ": 274,
284
+ "ዲ": 275,
285
+ "ዳ": 276,
286
+ "ዴ": 277,
287
+ "ድ": 278,
288
+ "ዶ": 279,
289
+ "ዷ": 280,
290
+ "ዸ": 281,
291
+ "ዹ": 282,
292
+ "ዺ": 283,
293
+ "ዻ": 284,
294
+ "ዼ": 285,
295
+ "ዽ": 286,
296
+ "ዾ": 287,
297
+ "ዿ": 288,
298
+ "ጀ": 289,
299
+ "ጁ": 290,
300
+ "ጂ": 291,
301
+ "ጃ": 292,
302
+ "ጄ": 293,
303
+ "ጅ": 294,
304
+ "ጆ": 295,
305
+ "ጇ": 296,
306
+ "ገ": 297,
307
+ "ጉ": 298,
308
+ "ጊ": 299,
309
+ "ጋ": 300,
310
+ "ጌ": 301,
311
+ "ግ": 302,
312
+ "ጎ": 303,
313
+ "ጏ": 304,
314
+ "ጐ": 305,
315
+ "ጒ": 306,
316
+ "ጓ": 307,
317
+ "ጔ": 308,
318
+ "ጕ": 309,
319
+ "ጘ": 310,
320
+ "ጙ": 311,
321
+ "ጚ": 312,
322
+ "ጛ": 313,
323
+ "ጜ": 314,
324
+ "ጝ": 315,
325
+ "ጞ": 316,
326
+ "ጟ": 317,
327
+ "ጠ": 318,
328
+ "ጡ": 319,
329
+ "ጢ": 320,
330
+ "ጣ": 321,
331
+ "ጤ": 322,
332
+ "ጥ": 323,
333
+ "ጦ": 324,
334
+ "ጧ": 325,
335
+ "ጨ": 326,
336
+ "ጩ": 327,
337
+ "ጪ": 328,
338
+ "ጫ": 329,
339
+ "ጬ": 330,
340
+ "ጭ": 331,
341
+ "ጮ": 332,
342
+ "ጯ": 333,
343
+ "ጰ": 334,
344
+ "ጱ": 335,
345
+ "ጲ": 336,
346
+ "ጳ": 337,
347
+ "ጴ": 338,
348
+ "ጵ": 339,
349
+ "ጶ": 340,
350
+ "ጷ": 341,
351
+ "ጸ": 342,
352
+ "ጹ": 343,
353
+ "ጺ": 344,
354
+ "ጻ": 345,
355
+ "ጼ": 346,
356
+ "ጽ": 347,
357
+ "ጾ": 348,
358
+ "ጿ": 349,
359
+ "ፀ": 350,
360
+ "ፁ": 351,
361
+ "ፂ": 352,
362
+ "ፃ": 353,
363
+ "ፄ": 354,
364
+ "ፅ": 355,
365
+ "ፆ": 356,
366
+ "ፇ": 357,
367
+ "ፈ": 358,
368
+ "ፉ": 359,
369
+ "ፊ": 360,
370
+ "ፋ": 361,
371
+ "ፌ": 362,
372
+ "ፍ": 363,
373
+ "ፎ": 364,
374
+ "ፏ": 365,
375
+ "ፐ": 366,
376
+ "ፑ": 367,
377
+ "ፒ": 368,
378
+ "ፓ": 369,
379
+ "ፔ": 370,
380
+ "ፕ": 371,
381
+ "ፖ": 372,
382
+ "ፗ": 373,
383
+ "ፘ": 374,
384
+ "ፙ": 375,
385
+ "ፚ": 376,
386
+ "፠": 377,
387
+ "፡": 378,
388
+ "።": 379,
389
+ "፣": 380,
390
+ "፤": 381,
391
+ "፥": 382,
392
+ "፦": 383,
393
+ "፧": 384,
394
+ "፨": 385,
395
+ "፩": 386,
396
+ "፪": 387,
397
+ "፫": 388,
398
+ "፬": 389,
399
+ "፭": 390,
400
+ "፮": 391,
401
+ "፯": 392,
402
+ "፰": 393,
403
+ "፱": 394,
404
+ "፲": 395,
405
+ "፳": 396,
406
+ "፴": 397,
407
+ "፵": 398,
408
+ "፶": 399,
409
+ "፷": 400,
410
+ "፸": 401,
411
+ "፹": 402,
412
+ "፺": 403,
413
+ "፻": 404,
414
+ "፼": 405,
415
+ "€": 406
416
+ }