ylacombe HF staff commited on
Commit
56eb7f5
1 Parent(s): 4baa61e

Upload model

Browse files
Files changed (3) hide show
  1. config.json +243 -65
  2. generation_config.json +2 -1
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,166 +1,344 @@
1
  {
 
 
 
 
 
2
  "coarse_acoustics_config": {
3
- "_from_model_config": false,
 
 
 
 
4
  "bad_words_ids": null,
5
  "begin_suppress_tokens": null,
 
 
6
  "bos_token_id": null,
7
- "coarse_infer_token": 12050,
8
- "coarse_rate_hz": 75,
9
- "coarse_semantic_pad_token": 12048,
10
- "constraints": null,
11
  "decoder_start_token_id": null,
12
  "diversity_penalty": 0.0,
13
- "do_sample": true,
 
14
  "early_stopping": false,
15
  "encoder_no_repeat_ngram_size": 0,
16
- "encoder_repetition_penalty": 1.0,
17
  "eos_token_id": null,
18
- "epsilon_cutoff": 0.0,
19
- "eta_cutoff": 0.0,
20
  "exponential_decay_length_penalty": null,
21
- "force_words_ids": null,
22
  "forced_bos_token_id": null,
23
- "forced_decoder_ids": null,
24
  "forced_eos_token_id": null,
25
- "generation_kwargs": {},
 
 
 
 
 
 
 
 
 
 
 
 
26
  "length_penalty": 1.0,
27
- "max_coarse_history": 630,
28
- "max_coarse_input_length": 256,
29
  "max_length": 20,
30
- "max_new_tokens": null,
31
- "max_time": null,
32
  "min_length": 0,
33
- "min_new_tokens": null,
34
- "n_coarse_codebooks": 2,
 
35
  "no_repeat_ngram_size": 0,
36
  "num_beam_groups": 1,
37
  "num_beams": 1,
 
 
38
  "num_return_sequences": 1,
39
  "output_attentions": false,
40
  "output_hidden_states": false,
41
  "output_scores": false,
 
42
  "pad_token_id": null,
43
- "penalty_alpha": null,
 
 
44
  "remove_invalid_values": false,
45
- "renormalize_logits": true,
46
  "repetition_penalty": 1.0,
 
47
  "return_dict_in_generate": false,
48
- "sliding_window_len": 60,
49
  "suppress_tokens": null,
50
- "temperature": 0.7,
 
 
 
 
 
51
  "top_k": 50,
52
  "top_p": 1.0,
 
 
53
  "transformers_version": "4.31.0.dev0",
54
  "typical_p": 1.0,
 
55
  "use_cache": true
56
  },
57
- "codebook_size": 1024,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  "fine_acoustics_config": {
59
- "_from_model_config": false,
 
 
 
 
60
  "bad_words_ids": null,
61
  "begin_suppress_tokens": null,
 
 
62
  "bos_token_id": null,
63
- "constraints": null,
 
64
  "decoder_start_token_id": null,
65
  "diversity_penalty": 0.0,
66
  "do_sample": false,
 
67
  "early_stopping": false,
68
  "encoder_no_repeat_ngram_size": 0,
69
- "encoder_repetition_penalty": 1.0,
70
  "eos_token_id": null,
71
- "epsilon_cutoff": 0.0,
72
- "eta_cutoff": 0.0,
73
  "exponential_decay_length_penalty": null,
74
- "force_words_ids": null,
75
  "forced_bos_token_id": null,
76
- "forced_decoder_ids": null,
77
  "forced_eos_token_id": null,
78
- "generation_kwargs": {},
 
 
 
 
 
 
 
 
 
 
 
 
79
  "length_penalty": 1.0,
80
- "max_fine_history_length": 512,
81
- "max_fine_input_length": 1024,
82
  "max_length": 20,
83
- "max_new_tokens": null,
84
- "max_time": null,
85
  "min_length": 0,
86
- "min_new_tokens": null,
87
- "n_fine_codebooks": 8,
 
88
  "no_repeat_ngram_size": 0,
89
  "num_beam_groups": 1,
90
  "num_beams": 1,
 
 
91
  "num_return_sequences": 1,
92
  "output_attentions": false,
93
  "output_hidden_states": false,
94
  "output_scores": false,
 
95
  "pad_token_id": null,
96
- "penalty_alpha": null,
 
 
97
  "remove_invalid_values": false,
98
- "renormalize_logits": false,
99
  "repetition_penalty": 1.0,
 
100
  "return_dict_in_generate": false,
 
101
  "suppress_tokens": null,
102
- "temperature": 0.5,
 
 
 
 
 
103
  "top_k": 50,
104
  "top_p": 1.0,
 
 
105
  "transformers_version": "4.31.0.dev0",
106
  "typical_p": 1.0,
 
107
  "use_cache": true
108
  },
 
109
  "model_type": "bark",
110
- "sample_rate": 24000,
111
  "semantic_config": {
112
- "_from_model_config": false,
 
 
 
 
113
  "bad_words_ids": null,
114
  "begin_suppress_tokens": null,
 
 
115
  "bos_token_id": null,
116
- "constraints": null,
 
117
  "decoder_start_token_id": null,
118
  "diversity_penalty": 0.0,
119
- "do_sample": true,
 
120
  "early_stopping": false,
121
  "encoder_no_repeat_ngram_size": 0,
122
- "encoder_repetition_penalty": 1.0,
123
- "eos_token_id": 10000,
124
- "epsilon_cutoff": 0.0,
125
- "eta_cutoff": 0.0,
126
  "exponential_decay_length_penalty": null,
127
- "force_words_ids": null,
128
  "forced_bos_token_id": null,
129
- "forced_decoder_ids": null,
130
  "forced_eos_token_id": null,
131
- "generation_kwargs": {},
 
 
 
 
 
 
 
 
 
 
 
 
132
  "length_penalty": 1.0,
133
- "max_input_semantic_length": 256,
134
  "max_length": 20,
135
- "max_new_tokens": 768,
136
- "max_time": null,
137
  "min_length": 0,
138
- "min_new_tokens": null,
 
 
139
  "no_repeat_ngram_size": 0,
140
  "num_beam_groups": 1,
141
  "num_beams": 1,
 
 
142
  "num_return_sequences": 1,
143
  "output_attentions": false,
144
  "output_hidden_states": false,
145
  "output_scores": false,
 
146
  "pad_token_id": null,
147
- "penalty_alpha": null,
 
 
148
  "remove_invalid_values": false,
149
- "renormalize_logits": true,
150
  "repetition_penalty": 1.0,
 
151
  "return_dict_in_generate": false,
152
- "semantic_infer_token": 129599,
153
- "semantic_pad_token": 10000,
154
- "semantic_rate_hz": 49.9,
155
- "semantic_vocab_size": 10000,
156
  "suppress_tokens": null,
157
- "temperature": 0.7,
158
- "text_encoding_offset": 10048,
159
- "text_pad_token": 129595,
 
 
 
160
  "top_k": 50,
161
  "top_p": 1.0,
 
 
162
  "transformers_version": "4.31.0.dev0",
163
  "typical_p": 1.0,
 
164
  "use_cache": true
165
- }
 
 
166
  }
 
1
  {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/home/yoach/bark_weigths/model/",
4
+ "architectures": [
5
+ "BarkModel"
6
+ ],
7
  "coarse_acoustics_config": {
8
+ "_name_or_path": "",
9
+ "add_cross_attention": false,
10
+ "architectures": [
11
+ "BarkCoarseModel"
12
+ ],
13
  "bad_words_ids": null,
14
  "begin_suppress_tokens": null,
15
+ "bias": false,
16
+ "block_size": 1024,
17
  "bos_token_id": null,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
 
 
20
  "decoder_start_token_id": null,
21
  "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "dropout": 0.0,
24
  "early_stopping": false,
25
  "encoder_no_repeat_ngram_size": 0,
 
26
  "eos_token_id": null,
 
 
27
  "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
  "forced_bos_token_id": null,
 
30
  "forced_eos_token_id": null,
31
+ "hidden_size": 1024,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "input_vocab_size": 12096,
38
+ "is_decoder": false,
39
+ "is_encoder_decoder": false,
40
+ "label2id": {
41
+ "LABEL_0": 0,
42
+ "LABEL_1": 1
43
+ },
44
  "length_penalty": 1.0,
 
 
45
  "max_length": 20,
 
 
46
  "min_length": 0,
47
+ "model_type": "coarse_acoustics",
48
+ "n_codes_given": 1,
49
+ "n_codes_total": 8,
50
  "no_repeat_ngram_size": 0,
51
  "num_beam_groups": 1,
52
  "num_beams": 1,
53
+ "num_heads": 16,
54
+ "num_layers": 24,
55
  "num_return_sequences": 1,
56
  "output_attentions": false,
57
  "output_hidden_states": false,
58
  "output_scores": false,
59
+ "output_vocab_size": 12096,
60
  "pad_token_id": null,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
  "remove_invalid_values": false,
 
65
  "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
  "return_dict_in_generate": false,
68
+ "sep_token_id": null,
69
  "suppress_tokens": null,
70
+ "task_specific_params": null,
71
+ "temperature": 1.0,
72
+ "tf_legacy_loss": false,
73
+ "tie_encoder_decoder": false,
74
+ "tie_word_embeddings": true,
75
+ "tokenizer_class": null,
76
  "top_k": 50,
77
  "top_p": 1.0,
78
+ "torch_dtype": "float32",
79
+ "torchscript": false,
80
  "transformers_version": "4.31.0.dev0",
81
  "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
  "use_cache": true
84
  },
85
+ "codec_config": {
86
+ "_name_or_path": "ArthurZ/encodec_24khz",
87
+ "add_cross_attention": false,
88
+ "architectures": [
89
+ "EncodecModel"
90
+ ],
91
+ "audio_channels": 1,
92
+ "bad_words_ids": null,
93
+ "begin_suppress_tokens": null,
94
+ "bos_token_id": null,
95
+ "chunk_length_s": null,
96
+ "chunk_size_feed_forward": 0,
97
+ "codebook_dim": 128,
98
+ "codebook_size": 1024,
99
+ "compress": 2,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "dilation_growth_rate": 2,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": null,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_size": 128,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "is_decoder": false,
118
+ "is_encoder_decoder": false,
119
+ "kernel_size": 7,
120
+ "label2id": {
121
+ "LABEL_0": 0,
122
+ "LABEL_1": 1
123
+ },
124
+ "last_kernel_size": 7,
125
+ "length_penalty": 1.0,
126
+ "max_length": 20,
127
+ "min_length": 0,
128
+ "model_type": "encodec",
129
+ "no_repeat_ngram_size": 0,
130
+ "norm_type": "weight_norm",
131
+ "normalize": false,
132
+ "num_beam_groups": 1,
133
+ "num_beams": 1,
134
+ "num_filters": 32,
135
+ "num_lstm_layers": 2,
136
+ "num_residual_layers": 1,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "overlap": null,
142
+ "pad_mode": "reflect",
143
+ "pad_token_id": null,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "pruned_heads": {},
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "residual_kernel_size": 3,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sampling_rate": 24000,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "target_bandwidths": [
156
+ 1.5,
157
+ 3.0,
158
+ 6.0,
159
+ 12.0,
160
+ 24.0
161
+ ],
162
+ "task_specific_params": null,
163
+ "temperature": 1.0,
164
+ "tf_legacy_loss": false,
165
+ "tie_encoder_decoder": false,
166
+ "tie_word_embeddings": true,
167
+ "tokenizer_class": null,
168
+ "top_k": 50,
169
+ "top_p": 1.0,
170
+ "torch_dtype": "float32",
171
+ "torchscript": false,
172
+ "transformers_version": "4.31.0.dev0",
173
+ "trim_right_ratio": 1.0,
174
+ "typical_p": 1.0,
175
+ "upsampling_ratios": [
176
+ 8,
177
+ 5,
178
+ 4,
179
+ 2
180
+ ],
181
+ "use_bfloat16": false,
182
+ "use_causal_conv": true
183
+ },
184
  "fine_acoustics_config": {
185
+ "_name_or_path": "",
186
+ "add_cross_attention": false,
187
+ "architectures": [
188
+ "BarkFineModel"
189
+ ],
190
  "bad_words_ids": null,
191
  "begin_suppress_tokens": null,
192
+ "bias": false,
193
+ "block_size": 1024,
194
  "bos_token_id": null,
195
+ "chunk_size_feed_forward": 0,
196
+ "cross_attention_hidden_size": null,
197
  "decoder_start_token_id": null,
198
  "diversity_penalty": 0.0,
199
  "do_sample": false,
200
+ "dropout": 0.0,
201
  "early_stopping": false,
202
  "encoder_no_repeat_ngram_size": 0,
 
203
  "eos_token_id": null,
 
 
204
  "exponential_decay_length_penalty": null,
205
+ "finetuning_task": null,
206
  "forced_bos_token_id": null,
 
207
  "forced_eos_token_id": null,
208
+ "hidden_size": 1024,
209
+ "id2label": {
210
+ "0": "LABEL_0",
211
+ "1": "LABEL_1"
212
+ },
213
+ "initializer_range": 0.02,
214
+ "input_vocab_size": 1056,
215
+ "is_decoder": false,
216
+ "is_encoder_decoder": false,
217
+ "label2id": {
218
+ "LABEL_0": 0,
219
+ "LABEL_1": 1
220
+ },
221
  "length_penalty": 1.0,
 
 
222
  "max_length": 20,
 
 
223
  "min_length": 0,
224
+ "model_type": "fine_acoustics",
225
+ "n_codes_given": 1,
226
+ "n_codes_total": 8,
227
  "no_repeat_ngram_size": 0,
228
  "num_beam_groups": 1,
229
  "num_beams": 1,
230
+ "num_heads": 16,
231
+ "num_layers": 24,
232
  "num_return_sequences": 1,
233
  "output_attentions": false,
234
  "output_hidden_states": false,
235
  "output_scores": false,
236
+ "output_vocab_size": 1056,
237
  "pad_token_id": null,
238
+ "prefix": null,
239
+ "problem_type": null,
240
+ "pruned_heads": {},
241
  "remove_invalid_values": false,
 
242
  "repetition_penalty": 1.0,
243
+ "return_dict": true,
244
  "return_dict_in_generate": false,
245
+ "sep_token_id": null,
246
  "suppress_tokens": null,
247
+ "task_specific_params": null,
248
+ "temperature": 1.0,
249
+ "tf_legacy_loss": false,
250
+ "tie_encoder_decoder": false,
251
+ "tie_word_embeddings": true,
252
+ "tokenizer_class": null,
253
  "top_k": 50,
254
  "top_p": 1.0,
255
+ "torch_dtype": "float32",
256
+ "torchscript": false,
257
  "transformers_version": "4.31.0.dev0",
258
  "typical_p": 1.0,
259
+ "use_bfloat16": false,
260
  "use_cache": true
261
  },
262
+ "initializer_range": 0.02,
263
  "model_type": "bark",
 
264
  "semantic_config": {
265
+ "_name_or_path": "",
266
+ "add_cross_attention": false,
267
+ "architectures": [
268
+ "BarkSemanticModel"
269
+ ],
270
  "bad_words_ids": null,
271
  "begin_suppress_tokens": null,
272
+ "bias": false,
273
+ "block_size": 1024,
274
  "bos_token_id": null,
275
+ "chunk_size_feed_forward": 0,
276
+ "cross_attention_hidden_size": null,
277
  "decoder_start_token_id": null,
278
  "diversity_penalty": 0.0,
279
+ "do_sample": false,
280
+ "dropout": 0.0,
281
  "early_stopping": false,
282
  "encoder_no_repeat_ngram_size": 0,
283
+ "eos_token_id": null,
 
 
 
284
  "exponential_decay_length_penalty": null,
285
+ "finetuning_task": null,
286
  "forced_bos_token_id": null,
 
287
  "forced_eos_token_id": null,
288
+ "hidden_size": 1024,
289
+ "id2label": {
290
+ "0": "LABEL_0",
291
+ "1": "LABEL_1"
292
+ },
293
+ "initializer_range": 0.02,
294
+ "input_vocab_size": 129600,
295
+ "is_decoder": false,
296
+ "is_encoder_decoder": false,
297
+ "label2id": {
298
+ "LABEL_0": 0,
299
+ "LABEL_1": 1
300
+ },
301
  "length_penalty": 1.0,
 
302
  "max_length": 20,
 
 
303
  "min_length": 0,
304
+ "model_type": "semantic",
305
+ "n_codes_given": 1,
306
+ "n_codes_total": 8,
307
  "no_repeat_ngram_size": 0,
308
  "num_beam_groups": 1,
309
  "num_beams": 1,
310
+ "num_heads": 16,
311
+ "num_layers": 24,
312
  "num_return_sequences": 1,
313
  "output_attentions": false,
314
  "output_hidden_states": false,
315
  "output_scores": false,
316
+ "output_vocab_size": 10048,
317
  "pad_token_id": null,
318
+ "prefix": null,
319
+ "problem_type": null,
320
+ "pruned_heads": {},
321
  "remove_invalid_values": false,
 
322
  "repetition_penalty": 1.0,
323
+ "return_dict": true,
324
  "return_dict_in_generate": false,
325
+ "sep_token_id": null,
 
 
 
326
  "suppress_tokens": null,
327
+ "task_specific_params": null,
328
+ "temperature": 1.0,
329
+ "tf_legacy_loss": false,
330
+ "tie_encoder_decoder": false,
331
+ "tie_word_embeddings": true,
332
+ "tokenizer_class": null,
333
  "top_k": 50,
334
  "top_p": 1.0,
335
+ "torch_dtype": "float32",
336
+ "torchscript": false,
337
  "transformers_version": "4.31.0.dev0",
338
  "typical_p": 1.0,
339
+ "use_bfloat16": false,
340
  "use_cache": true
341
+ },
342
+ "torch_dtype": "float32",
343
+ "transformers_version": null
344
  }
generation_config.json CHANGED
@@ -162,5 +162,6 @@
162
  "transformers_version": "4.31.0.dev0",
163
  "typical_p": 1.0,
164
  "use_cache": true
165
- }
 
166
  }
 
162
  "transformers_version": "4.31.0.dev0",
163
  "typical_p": 1.0,
164
  "use_cache": true
165
+ },
166
+ "transformers_version": "4.31.0.dev0"
167
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be95e5fee92f8134ed67ae5eb418f202af5d005a5a617ffeacf82b9326a7cd4e
3
- size 4486642261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9ac007f13624882c82d561378eb356321594eabf320fdbbe32c25b098dad4df
3
+ size 4516921809