alzavo commited on
Commit
2836bc8
·
verified ·
1 Parent(s): b19a727

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "</s>": 81,
3
+ "<s>": 80
4
+ }
config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GOPPhonemeClassifier"
4
+ ],
5
+ "base_model_name_or_path": "exp/ctc_model/TalTechNLP/xls-r-300m-et.a",
6
+ "bos_id": 80,
7
+ "bos_token_id": 80,
8
+ "ctc_config": {
9
+ "_name_or_path": "",
10
+ "activation_dropout": 0.1,
11
+ "adapter_attn_dim": null,
12
+ "adapter_kernel_size": 3,
13
+ "adapter_stride": 2,
14
+ "add_adapter": false,
15
+ "add_cross_attention": false,
16
+ "apply_spec_augment": true,
17
+ "architectures": [
18
+ "Wav2Vec2ForCTC"
19
+ ],
20
+ "attention_dropout": 0.0,
21
+ "bad_words_ids": null,
22
+ "begin_suppress_tokens": null,
23
+ "bos_token_id": 1,
24
+ "chunk_size_feed_forward": 0,
25
+ "classifier_proj_size": 256,
26
+ "codevector_dim": 768,
27
+ "contrastive_logits_temperature": 0.1,
28
+ "conv_bias": true,
29
+ "conv_dim": [
30
+ 512,
31
+ 512,
32
+ 512,
33
+ 512,
34
+ 512,
35
+ 512,
36
+ 512
37
+ ],
38
+ "conv_kernel": [
39
+ 10,
40
+ 3,
41
+ 3,
42
+ 3,
43
+ 3,
44
+ 2,
45
+ 2
46
+ ],
47
+ "conv_stride": [
48
+ 5,
49
+ 2,
50
+ 2,
51
+ 2,
52
+ 2,
53
+ 2,
54
+ 2
55
+ ],
56
+ "cross_attention_hidden_size": null,
57
+ "ctc_loss_reduction": "mean",
58
+ "ctc_zero_infinity": true,
59
+ "decoder_start_token_id": null,
60
+ "diversity_loss_weight": 0.1,
61
+ "diversity_penalty": 0.0,
62
+ "do_sample": false,
63
+ "do_stable_layer_norm": true,
64
+ "dtype": "float32",
65
+ "early_stopping": false,
66
+ "encoder_no_repeat_ngram_size": 0,
67
+ "eos_token_id": 2,
68
+ "exponential_decay_length_penalty": null,
69
+ "feat_extract_activation": "gelu",
70
+ "feat_extract_dropout": 0.0,
71
+ "feat_extract_norm": "layer",
72
+ "feat_proj_dropout": 0.0,
73
+ "feat_quantizer_dropout": 0.0,
74
+ "final_dropout": 0.0,
75
+ "finetuning_task": null,
76
+ "forced_bos_token_id": null,
77
+ "forced_eos_token_id": null,
78
+ "gradient_checkpointing": false,
79
+ "hidden_act": "gelu",
80
+ "hidden_dropout": 0.0,
81
+ "hidden_size": 1024,
82
+ "id2label": {
83
+ "0": "LABEL_0",
84
+ "1": "LABEL_1"
85
+ },
86
+ "initializer_range": 0.02,
87
+ "intermediate_size": 4096,
88
+ "is_decoder": false,
89
+ "is_encoder_decoder": false,
90
+ "label2id": {
91
+ "LABEL_0": 0,
92
+ "LABEL_1": 1
93
+ },
94
+ "layer_norm_eps": 1e-05,
95
+ "layerdrop": 0.0,
96
+ "length_penalty": 1.0,
97
+ "mask_feature_length": 64,
98
+ "mask_feature_min_masks": 0,
99
+ "mask_feature_prob": 0.004,
100
+ "mask_time_length": 10,
101
+ "mask_time_min_masks": 2,
102
+ "mask_time_prob": 0.0,
103
+ "max_length": 20,
104
+ "min_length": 0,
105
+ "model_type": "wav2vec2",
106
+ "no_repeat_ngram_size": 0,
107
+ "num_adapter_layers": 3,
108
+ "num_attention_heads": 16,
109
+ "num_beam_groups": 1,
110
+ "num_beams": 1,
111
+ "num_codevector_groups": 2,
112
+ "num_codevectors_per_group": 320,
113
+ "num_conv_pos_embedding_groups": 16,
114
+ "num_conv_pos_embeddings": 128,
115
+ "num_feat_extract_layers": 7,
116
+ "num_hidden_layers": 24,
117
+ "num_negatives": 100,
118
+ "num_return_sequences": 1,
119
+ "output_attentions": false,
120
+ "output_hidden_size": 1024,
121
+ "output_hidden_states": false,
122
+ "output_scores": false,
123
+ "pad_token_id": 79,
124
+ "prefix": null,
125
+ "problem_type": null,
126
+ "proj_codevector_dim": 768,
127
+ "pruned_heads": {},
128
+ "remove_invalid_values": false,
129
+ "repetition_penalty": 1.0,
130
+ "return_dict": true,
131
+ "return_dict_in_generate": false,
132
+ "sep_token_id": null,
133
+ "suppress_tokens": null,
134
+ "task_specific_params": null,
135
+ "tdnn_dilation": [
136
+ 1,
137
+ 2,
138
+ 3,
139
+ 1,
140
+ 1
141
+ ],
142
+ "tdnn_dim": [
143
+ 512,
144
+ 512,
145
+ 512,
146
+ 512,
147
+ 1500
148
+ ],
149
+ "tdnn_kernel": [
150
+ 5,
151
+ 3,
152
+ 3,
153
+ 1,
154
+ 1
155
+ ],
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": true,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torchscript": false,
164
+ "transformers_version": "4.56.2",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_weighted_layer_sum": false,
168
+ "vocab_size": 82,
169
+ "xvector_output_dim": 512
170
+ },
171
+ "dtype": "float32",
172
+ "eos_id": 81,
173
+ "eos_token_id": 81,
174
+ "gop_ce_weights": [
175
+ 0.357495626429821,
176
+ 5.765082465277777,
177
+ 34.12395632626846
178
+ ],
179
+ "gop_embedding_dim": 128,
180
+ "gop_loss_alpha": 0.5,
181
+ "gop_transformer_dim_feedforward": 512,
182
+ "gop_transformer_dropout": 0.1,
183
+ "gop_transformer_nhead": 4,
184
+ "gop_transformer_nlayers": 1,
185
+ "model_type": "gop-wav2vec2",
186
+ "num_gop_labels": 3,
187
+ "pad_id": 79,
188
+ "pad_token_id": 79,
189
+ "token_id_vocab": null,
190
+ "transformers_version": "4.56.2",
191
+ "unk_id": 78
192
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d37d885dbe0e9f041025c32023bc005283b7cb62ae66a1a458392edc08d73ac
3
+ size 1263748092
preprocessor_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "processor_class": "Wav2Vec2Processor",
8
+ "return_attention_mask": true,
9
+ "sampling_rate": 16000
10
+ }
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 +1,497 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "1": {
4
+ "content": "a:",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "2": {
12
+ "content": "aa",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": false
18
+ },
19
+ "3": {
20
+ "content": "aa:",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "5": {
28
+ "content": "e:",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "6": {
36
+ "content": "ee",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": true,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "7": {
44
+ "content": "ee:",
45
+ "lstrip": true,
46
+ "normalized": false,
47
+ "rstrip": true,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "9": {
52
+ "content": "ff",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "11": {
60
+ "content": "h:",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "13": {
68
+ "content": "i:",
69
+ "lstrip": true,
70
+ "normalized": false,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "14": {
76
+ "content": "ii",
77
+ "lstrip": true,
78
+ "normalized": false,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "15": {
84
+ "content": "ii:",
85
+ "lstrip": true,
86
+ "normalized": false,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "18": {
92
+ "content": "k:",
93
+ "lstrip": true,
94
+ "normalized": false,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "19": {
100
+ "content": "k:k",
101
+ "lstrip": true,
102
+ "normalized": false,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "20": {
108
+ "content": "kk",
109
+ "lstrip": true,
110
+ "normalized": false,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "22": {
116
+ "content": "l'",
117
+ "lstrip": true,
118
+ "normalized": false,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "23": {
124
+ "content": "l':l",
125
+ "lstrip": true,
126
+ "normalized": false,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "24": {
132
+ "content": "l'l",
133
+ "lstrip": true,
134
+ "normalized": false,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "25": {
140
+ "content": "l:",
141
+ "lstrip": true,
142
+ "normalized": false,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "26": {
148
+ "content": "l:l",
149
+ "lstrip": true,
150
+ "normalized": false,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "27": {
156
+ "content": "ll",
157
+ "lstrip": true,
158
+ "normalized": false,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "29": {
164
+ "content": "m:",
165
+ "lstrip": true,
166
+ "normalized": false,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "30": {
172
+ "content": "mm",
173
+ "lstrip": true,
174
+ "normalized": false,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "32": {
180
+ "content": "n'",
181
+ "lstrip": true,
182
+ "normalized": false,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "33": {
188
+ "content": "n':",
189
+ "lstrip": true,
190
+ "normalized": false,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "34": {
196
+ "content": "n':n",
197
+ "lstrip": true,
198
+ "normalized": false,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "35": {
204
+ "content": "n:",
205
+ "lstrip": true,
206
+ "normalized": false,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "36": {
212
+ "content": "n:n",
213
+ "lstrip": true,
214
+ "normalized": false,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "37": {
220
+ "content": "nn",
221
+ "lstrip": true,
222
+ "normalized": false,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "39": {
228
+ "content": "o:",
229
+ "lstrip": true,
230
+ "normalized": false,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "40": {
236
+ "content": "oo",
237
+ "lstrip": true,
238
+ "normalized": false,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "41": {
244
+ "content": "oo:",
245
+ "lstrip": true,
246
+ "normalized": false,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "43": {
252
+ "content": "p:p",
253
+ "lstrip": true,
254
+ "normalized": false,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "44": {
260
+ "content": "pp",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "46": {
268
+ "content": "r:",
269
+ "lstrip": true,
270
+ "normalized": false,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "47": {
276
+ "content": "rr",
277
+ "lstrip": true,
278
+ "normalized": false,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "49": {
284
+ "content": "s'",
285
+ "lstrip": true,
286
+ "normalized": false,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50": {
292
+ "content": "s':s",
293
+ "lstrip": true,
294
+ "normalized": false,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "51": {
300
+ "content": "s:",
301
+ "lstrip": true,
302
+ "normalized": false,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "52": {
308
+ "content": "s:s",
309
+ "lstrip": true,
310
+ "normalized": false,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "53": {
316
+ "content": "ss",
317
+ "lstrip": true,
318
+ "normalized": false,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "55": {
324
+ "content": "t'",
325
+ "lstrip": true,
326
+ "normalized": false,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "56": {
332
+ "content": "t':",
333
+ "lstrip": true,
334
+ "normalized": false,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "57": {
340
+ "content": "t':t",
341
+ "lstrip": true,
342
+ "normalized": false,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "58": {
348
+ "content": "t't",
349
+ "lstrip": true,
350
+ "normalized": false,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "59": {
356
+ "content": "t:",
357
+ "lstrip": true,
358
+ "normalized": false,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "60": {
364
+ "content": "t:t",
365
+ "lstrip": true,
366
+ "normalized": false,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "61": {
372
+ "content": "tt",
373
+ "lstrip": true,
374
+ "normalized": false,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "63": {
380
+ "content": "uu",
381
+ "lstrip": true,
382
+ "normalized": false,
383
+ "rstrip": true,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "64": {
388
+ "content": "uu:",
389
+ "lstrip": true,
390
+ "normalized": false,
391
+ "rstrip": true,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "66": {
396
+ "content": "v:v",
397
+ "lstrip": true,
398
+ "normalized": false,
399
+ "rstrip": true,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "67": {
404
+ "content": "vv",
405
+ "lstrip": true,
406
+ "normalized": false,
407
+ "rstrip": true,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "70": {
412
+ "content": "ää",
413
+ "lstrip": true,
414
+ "normalized": false,
415
+ "rstrip": true,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "72": {
420
+ "content": "õõ",
421
+ "lstrip": true,
422
+ "normalized": false,
423
+ "rstrip": true,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "74": {
428
+ "content": "öö",
429
+ "lstrip": true,
430
+ "normalized": false,
431
+ "rstrip": true,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "75": {
436
+ "content": "öö:",
437
+ "lstrip": true,
438
+ "normalized": false,
439
+ "rstrip": true,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "77": {
444
+ "content": "üü",
445
+ "lstrip": true,
446
+ "normalized": false,
447
+ "rstrip": true,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "78": {
452
+ "content": "[UNK]",
453
+ "lstrip": true,
454
+ "normalized": false,
455
+ "rstrip": true,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "79": {
460
+ "content": "[PAD]",
461
+ "lstrip": true,
462
+ "normalized": false,
463
+ "rstrip": true,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "80": {
468
+ "content": "<s>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "81": {
476
+ "content": "</s>",
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
+ "processor_class": "Wav2Vec2Processor",
492
+ "replace_word_delimiter_char": " ",
493
+ "target_lang": null,
494
+ "tokenizer_class": "Wav2Vec2CTCTokenizer",
495
+ "unk_token": "[UNK]",
496
+ "word_delimiter_token": "None"
497
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d42058caca0fe4a19d8d22e22d3bd14f0ae76650674747930af328ad35fcf8e8
3
+ size 5777
vocab.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "[PAD]": 79,
3
+ "[UNK]": 78,
4
+ "a": 0,
5
+ "a:": 1,
6
+ "aa": 2,
7
+ "aa:": 3,
8
+ "e": 4,
9
+ "e:": 5,
10
+ "ee": 6,
11
+ "ee:": 7,
12
+ "f": 8,
13
+ "ff": 9,
14
+ "h": 10,
15
+ "h:": 11,
16
+ "i": 12,
17
+ "i:": 13,
18
+ "ii": 14,
19
+ "ii:": 15,
20
+ "j": 16,
21
+ "k": 17,
22
+ "k:": 18,
23
+ "k:k": 19,
24
+ "kk": 20,
25
+ "l": 21,
26
+ "l'": 22,
27
+ "l':l": 23,
28
+ "l'l": 24,
29
+ "l:": 25,
30
+ "l:l": 26,
31
+ "ll": 27,
32
+ "m": 28,
33
+ "m:": 29,
34
+ "mm": 30,
35
+ "n": 31,
36
+ "n'": 32,
37
+ "n':": 33,
38
+ "n':n": 34,
39
+ "n:": 35,
40
+ "n:n": 36,
41
+ "nn": 37,
42
+ "o": 38,
43
+ "o:": 39,
44
+ "oo": 40,
45
+ "oo:": 41,
46
+ "p": 42,
47
+ "p:p": 43,
48
+ "pp": 44,
49
+ "r": 45,
50
+ "r:": 46,
51
+ "rr": 47,
52
+ "s": 48,
53
+ "s'": 49,
54
+ "s':s": 50,
55
+ "s:": 51,
56
+ "s:s": 52,
57
+ "ss": 53,
58
+ "t": 54,
59
+ "t'": 55,
60
+ "t':": 56,
61
+ "t':t": 57,
62
+ "t't": 58,
63
+ "t:": 59,
64
+ "t:t": 60,
65
+ "tt": 61,
66
+ "u": 62,
67
+ "uu": 63,
68
+ "uu:": 64,
69
+ "v": 65,
70
+ "v:v": 66,
71
+ "vv": 67,
72
+ "|": 68,
73
+ "ä": 69,
74
+ "ää": 70,
75
+ "õ": 71,
76
+ "õõ": 72,
77
+ "ö": 73,
78
+ "öö": 74,
79
+ "öö:": 75,
80
+ "ü": 76,
81
+ "üü": 77
82
+ }