Hugging Face's logo

adamchant
/
baseline_universal_phone_120k

Text-to-Audio
Transformers
PyTorch
TensorBoard
speecht5
Inference Endpoints
Model card Files Metrics Community
adamchant commited on
Commit
9e0fd25
•
1 Parent(s): c2b6a86

Training in progress, step 5000

Browse files
Files changed (9) hide show
  1. added_tokens.json +45 -0
  2. config.json +92 -0
  3. preprocessor_config.json +19 -0
  4. pytorch_model.bin +3 -0
  5. runs/Nov07_04-51-19_de8039c9a22e/events.out.tfevents.1699332682.de8039c9a22e.26303.0 +3 -0
  6. special_tokens_map.json +37 -0
  7. spm_char.model +3 -0
  8. tokenizer_config.json +391 -0
  9. training_args.bin +3 -0
added_tokens.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<ctc_blank>": 80,
3
+ "<mask>": 79,
4
+ "ŋ": 95,
5
+ "ɑ": 85,
6
+ "ɕ": 114,
7
+ "ɖ": 96,
8
+ "ɗ": 89,
9
+ "ɛ": 107,
10
+ "ɝ": 91,
11
+ "ɞ": 87,
12
+ "ɦ": 104,
13
+ "ɨ": 99,
14
+ "ɫ": 110,
15
+ "ɬ": 102,
16
+ "ɮ": 105,
17
+ "ɱ": 93,
18
+ "ɲ": 103,
19
+ "ɳ": 117,
20
+ "ɴ": 121,
21
+ "ʀ": 101,
22
+ "ʂ": 84,
23
+ "ʃ": 83,
24
+ "ʈ": 81,
25
+ "ʉ": 94,
26
+ "ʊ": 86,
27
+ "ʋ": 119,
28
+ "ʎ": 115,
29
+ "ʏ": 108,
30
+ "ʔ": 111,
31
+ "ʧ": 113,
32
+ "ʯ": 82,
33
+ "Α": 106,
34
+ "Ι": 109,
35
+ "Ο": 118,
36
+ "β": 92,
37
+ "γ": 90,
38
+ "θ": 88,
39
+ "κ": 120,
40
+ "ο": 98,
41
+ "π": 100,
42
+ "ρ": 116,
43
+ "ϝ": 112,
44
+ "ϳ": 97
45
+ }
config.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "model_t5",
3
+ "activation_dropout": 0.1,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "SpeechT5ForTextToSpeech"
7
+ ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "conv_bias": false,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "decoder_attention_heads": 12,
39
+ "decoder_ffn_dim": 3072,
40
+ "decoder_layerdrop": 0.1,
41
+ "decoder_layers": 6,
42
+ "decoder_start_token_id": 2,
43
+ "encoder_attention_heads": 12,
44
+ "encoder_ffn_dim": 3072,
45
+ "encoder_layerdrop": 0.1,
46
+ "encoder_layers": 12,
47
+ "encoder_max_relative_position": 160,
48
+ "eos_token_id": 2,
49
+ "feat_extract_activation": "gelu",
50
+ "feat_extract_norm": "group",
51
+ "feat_proj_dropout": 0.0,
52
+ "guided_attention_loss_num_heads": 2,
53
+ "guided_attention_loss_scale": 10.0,
54
+ "guided_attention_loss_sigma": 0.4,
55
+ "hidden_act": "gelu",
56
+ "hidden_dropout": 0.1,
57
+ "hidden_size": 768,
58
+ "initializer_range": 0.02,
59
+ "is_encoder_decoder": true,
60
+ "layer_norm_eps": 1e-05,
61
+ "mask_feature_length": 10,
62
+ "mask_feature_min_masks": 0,
63
+ "mask_feature_prob": 0.0,
64
+ "mask_time_length": 10,
65
+ "mask_time_min_masks": 2,
66
+ "mask_time_prob": 0.05,
67
+ "max_length": 1876,
68
+ "max_speech_positions": 1876,
69
+ "max_text_positions": 600,
70
+ "model_type": "speecht5",
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_mel_bins": 80,
75
+ "pad_token_id": 1,
76
+ "positional_dropout": 0.1,
77
+ "reduction_factor": 2,
78
+ "scale_embedding": false,
79
+ "speaker_embedding_dim": 512,
80
+ "speech_decoder_postnet_dropout": 0.5,
81
+ "speech_decoder_postnet_kernel": 5,
82
+ "speech_decoder_postnet_layers": 5,
83
+ "speech_decoder_postnet_units": 256,
84
+ "speech_decoder_prenet_dropout": 0.5,
85
+ "speech_decoder_prenet_layers": 2,
86
+ "speech_decoder_prenet_units": 256,
87
+ "torch_dtype": "float32",
88
+ "transformers_version": "4.35.0.dev0",
89
+ "use_cache": false,
90
+ "use_guided_attention_loss": true,
91
+ "vocab_size": 122
92
+ }
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
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d7db6a2f14474feab845d97f030969a20e3469834d35b7c47e07208083154c3
3
+ size 578004730
runs/Nov07_04-51-19_de8039c9a22e/events.out.tfevents.1699332682.de8039c9a22e.26303.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16955e942d49c87b53da92599f72df5b9d58f567a3133f89eb3c6a669520f124
3
+ size 38519
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": true,
5
+ "normalized": false,
6
+ "rstrip": true,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": true,
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": true,
26
+ "normalized": false,
27
+ "rstrip": true,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": true,
33
+ "normalized": false,
34
+ "rstrip": true,
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 +1,391 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": true,
6
+ "normalized": false,
7
+ "rstrip": true,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": true,
14
+ "normalized": false,
15
+ "rstrip": true,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": true,
22
+ "normalized": false,
23
+ "rstrip": true,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": true,
30
+ "normalized": false,
31
+ "rstrip": true,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "79": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "80": {
44
+ "content": "<ctc_blank>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "81": {
52
+ "content": "ʈ",
53
+ "lstrip": true,
54
+ "normalized": true,
55
+ "rstrip": true,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "82": {
60
+ "content": "ʯ",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": true,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "83": {
68
+ "content": "ʃ",
69
+ "lstrip": true,
70
+ "normalized": true,
71
+ "rstrip": true,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "84": {
76
+ "content": "ʂ",
77
+ "lstrip": true,
78
+ "normalized": true,
79
+ "rstrip": true,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "85": {
84
+ "content": "ɑ",
85
+ "lstrip": true,
86
+ "normalized": true,
87
+ "rstrip": true,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "86": {
92
+ "content": "ʊ",
93
+ "lstrip": true,
94
+ "normalized": true,
95
+ "rstrip": true,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "87": {
100
+ "content": "ɞ",
101
+ "lstrip": true,
102
+ "normalized": true,
103
+ "rstrip": true,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "88": {
108
+ "content": "θ",
109
+ "lstrip": true,
110
+ "normalized": true,
111
+ "rstrip": true,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "89": {
116
+ "content": "ɗ",
117
+ "lstrip": true,
118
+ "normalized": true,
119
+ "rstrip": true,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "90": {
124
+ "content": "γ",
125
+ "lstrip": true,
126
+ "normalized": true,
127
+ "rstrip": true,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "91": {
132
+ "content": "ɝ",
133
+ "lstrip": true,
134
+ "normalized": true,
135
+ "rstrip": true,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "92": {
140
+ "content": "β",
141
+ "lstrip": true,
142
+ "normalized": true,
143
+ "rstrip": true,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "93": {
148
+ "content": "ɱ",
149
+ "lstrip": true,
150
+ "normalized": true,
151
+ "rstrip": true,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "94": {
156
+ "content": "ʉ",
157
+ "lstrip": true,
158
+ "normalized": true,
159
+ "rstrip": true,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "95": {
164
+ "content": "ŋ",
165
+ "lstrip": true,
166
+ "normalized": true,
167
+ "rstrip": true,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "96": {
172
+ "content": "ɖ",
173
+ "lstrip": true,
174
+ "normalized": true,
175
+ "rstrip": true,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "97": {
180
+ "content": "ϳ",
181
+ "lstrip": true,
182
+ "normalized": true,
183
+ "rstrip": true,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "98": {
188
+ "content": "ο",
189
+ "lstrip": true,
190
+ "normalized": true,
191
+ "rstrip": true,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "99": {
196
+ "content": "ɨ",
197
+ "lstrip": true,
198
+ "normalized": true,
199
+ "rstrip": true,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "100": {
204
+ "content": "π",
205
+ "lstrip": true,
206
+ "normalized": true,
207
+ "rstrip": true,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "101": {
212
+ "content": "ʀ",
213
+ "lstrip": true,
214
+ "normalized": true,
215
+ "rstrip": true,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "102": {
220
+ "content": "ɬ",
221
+ "lstrip": true,
222
+ "normalized": true,
223
+ "rstrip": true,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "103": {
228
+ "content": "ɲ",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": true,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "104": {
236
+ "content": "ɦ",
237
+ "lstrip": true,
238
+ "normalized": true,
239
+ "rstrip": true,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "105": {
244
+ "content": "ɮ",
245
+ "lstrip": true,
246
+ "normalized": true,
247
+ "rstrip": true,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "106": {
252
+ "content": "Α",
253
+ "lstrip": true,
254
+ "normalized": true,
255
+ "rstrip": true,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "107": {
260
+ "content": "ɛ",
261
+ "lstrip": true,
262
+ "normalized": true,
263
+ "rstrip": true,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "108": {
268
+ "content": "ʏ",
269
+ "lstrip": true,
270
+ "normalized": true,
271
+ "rstrip": true,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "109": {
276
+ "content": "Ι",
277
+ "lstrip": true,
278
+ "normalized": true,
279
+ "rstrip": true,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "110": {
284
+ "content": "ɫ",
285
+ "lstrip": true,
286
+ "normalized": true,
287
+ "rstrip": true,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "111": {
292
+ "content": "ʔ",
293
+ "lstrip": true,
294
+ "normalized": true,
295
+ "rstrip": true,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "112": {
300
+ "content": "ϝ",
301
+ "lstrip": true,
302
+ "normalized": true,
303
+ "rstrip": true,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "113": {
308
+ "content": "ʧ",
309
+ "lstrip": true,
310
+ "normalized": true,
311
+ "rstrip": true,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "114": {
316
+ "content": "ɕ",
317
+ "lstrip": true,
318
+ "normalized": true,
319
+ "rstrip": true,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "115": {
324
+ "content": "ʎ",
325
+ "lstrip": true,
326
+ "normalized": true,
327
+ "rstrip": true,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "116": {
332
+ "content": "ρ",
333
+ "lstrip": true,
334
+ "normalized": true,
335
+ "rstrip": true,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "117": {
340
+ "content": "ɳ",
341
+ "lstrip": true,
342
+ "normalized": true,
343
+ "rstrip": true,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "118": {
348
+ "content": "Ο",
349
+ "lstrip": true,
350
+ "normalized": true,
351
+ "rstrip": true,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "119": {
356
+ "content": "ʋ",
357
+ "lstrip": true,
358
+ "normalized": true,
359
+ "rstrip": true,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "120": {
364
+ "content": "κ",
365
+ "lstrip": true,
366
+ "normalized": true,
367
+ "rstrip": true,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "121": {
372
+ "content": "ɴ",
373
+ "lstrip": true,
374
+ "normalized": true,
375
+ "rstrip": true,
376
+ "single_word": false,
377
+ "special": false
378
+ }
379
+ },
380
+ "bos_token": "<s>",
381
+ "clean_up_tokenization_spaces": true,
382
+ "eos_token": "</s>",
383
+ "mask_token": "<mask>",
384
+ "model_max_length": 600,
385
+ "normalize": false,
386
+ "pad_token": "<pad>",
387
+ "processor_class": "SpeechT5Processor",
388
+ "sp_model_kwargs": {},
389
+ "tokenizer_class": "SpeechT5Tokenizer",
390
+ "unk_token": "<unk>"
391
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e9b97c84f2dc6b32242b84cba2da977385b75151a8d1b8c928d91d7eaed5428
3
+ size 4664