Text-to-Speech
Transformers
Safetensors
English
parler_tts
text2text-generation
annotation
ylacombe HF staff commited on
Commit
5cc3f82
1 Parent(s): 70eccba

Upload StableSpeechForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +275 -0
  2. generation_config.json +11 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/fsx/yoach/tmp/artefacts/training-400M-punctuated-v2/",
3
+ "architectures": [
4
+ "StableSpeechForConditionalGeneration"
5
+ ],
6
+ "audio_encoder": {
7
+ "_name_or_path": "ylacombe/dac_44khZ_8kbps",
8
+ "add_cross_attention": false,
9
+ "architectures": [
10
+ "DACModel"
11
+ ],
12
+ "bad_words_ids": null,
13
+ "begin_suppress_tokens": null,
14
+ "bos_token_id": null,
15
+ "chunk_size_feed_forward": 0,
16
+ "codebook_size": 1024,
17
+ "cross_attention_hidden_size": null,
18
+ "decoder_start_token_id": null,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "early_stopping": false,
22
+ "encoder_no_repeat_ngram_size": 0,
23
+ "eos_token_id": null,
24
+ "exponential_decay_length_penalty": null,
25
+ "finetuning_task": null,
26
+ "forced_bos_token_id": null,
27
+ "forced_eos_token_id": null,
28
+ "frame_rate": 86,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "is_decoder": false,
34
+ "is_encoder_decoder": false,
35
+ "label2id": {
36
+ "LABEL_0": 0,
37
+ "LABEL_1": 1
38
+ },
39
+ "latent_dim": 1024,
40
+ "length_penalty": 1.0,
41
+ "max_length": 20,
42
+ "min_length": 0,
43
+ "model_bitrate": 8,
44
+ "model_type": "dac",
45
+ "no_repeat_ngram_size": 0,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_codebooks": 9,
49
+ "num_return_sequences": 1,
50
+ "output_attentions": false,
51
+ "output_hidden_states": false,
52
+ "output_scores": false,
53
+ "pad_token_id": null,
54
+ "prefix": null,
55
+ "problem_type": null,
56
+ "pruned_heads": {},
57
+ "remove_invalid_values": false,
58
+ "repetition_penalty": 1.0,
59
+ "return_dict": true,
60
+ "return_dict_in_generate": false,
61
+ "sep_token_id": null,
62
+ "suppress_tokens": null,
63
+ "task_specific_params": null,
64
+ "temperature": 1.0,
65
+ "tf_legacy_loss": false,
66
+ "tie_encoder_decoder": false,
67
+ "tie_word_embeddings": true,
68
+ "tokenizer_class": null,
69
+ "top_k": 50,
70
+ "top_p": 1.0,
71
+ "torch_dtype": "float32",
72
+ "torchscript": false,
73
+ "typical_p": 1.0,
74
+ "use_bfloat16": false
75
+ },
76
+ "decoder": {
77
+ "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
78
+ "activation_dropout": 0.0,
79
+ "activation_function": "gelu",
80
+ "add_cross_attention": true,
81
+ "architectures": [
82
+ "StableSpeechForCausalLM"
83
+ ],
84
+ "attention_dropout": 0.0,
85
+ "bad_words_ids": null,
86
+ "begin_suppress_tokens": null,
87
+ "bos_token_id": 1025,
88
+ "chunk_size_feed_forward": 0,
89
+ "cross_attention_hidden_size": null,
90
+ "decoder_start_token_id": null,
91
+ "diversity_penalty": 0.0,
92
+ "do_sample": false,
93
+ "dropout": 0.1,
94
+ "early_stopping": false,
95
+ "encoder_no_repeat_ngram_size": 0,
96
+ "eos_token_id": 1024,
97
+ "exponential_decay_length_penalty": null,
98
+ "ffn_dim": 4096,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "hidden_size": 1024,
103
+ "id2label": {
104
+ "0": "LABEL_0",
105
+ "1": "LABEL_1"
106
+ },
107
+ "initializer_factor": 0.02,
108
+ "is_decoder": true,
109
+ "is_encoder_decoder": false,
110
+ "label2id": {
111
+ "LABEL_0": 0,
112
+ "LABEL_1": 1
113
+ },
114
+ "layerdrop": 0.0,
115
+ "length_penalty": 1.0,
116
+ "max_length": 20,
117
+ "max_position_embeddings": 4096,
118
+ "min_length": 0,
119
+ "model_type": "stable_speech_decoder",
120
+ "no_repeat_ngram_size": 0,
121
+ "num_attention_heads": 16,
122
+ "num_beam_groups": 1,
123
+ "num_beams": 1,
124
+ "num_codebooks": 9,
125
+ "num_hidden_layers": 24,
126
+ "num_return_sequences": 1,
127
+ "output_attentions": false,
128
+ "output_hidden_states": false,
129
+ "output_scores": false,
130
+ "pad_token_id": 1024,
131
+ "prefix": null,
132
+ "problem_type": null,
133
+ "pruned_heads": {},
134
+ "remove_invalid_values": false,
135
+ "repetition_penalty": 1.0,
136
+ "return_dict": true,
137
+ "return_dict_in_generate": false,
138
+ "scale_embedding": false,
139
+ "sep_token_id": null,
140
+ "suppress_tokens": null,
141
+ "task_specific_params": null,
142
+ "temperature": 1.0,
143
+ "tf_legacy_loss": false,
144
+ "tie_encoder_decoder": false,
145
+ "tie_word_embeddings": false,
146
+ "tokenizer_class": null,
147
+ "top_k": 50,
148
+ "top_p": 1.0,
149
+ "torch_dtype": "float32",
150
+ "torchscript": false,
151
+ "typical_p": 1.0,
152
+ "use_bfloat16": false,
153
+ "use_cache": true,
154
+ "vocab_size": 1088
155
+ },
156
+ "decoder_start_token_id": 1025,
157
+ "is_encoder_decoder": true,
158
+ "model_type": "stable_speech",
159
+ "pad_token_id": 1024,
160
+ "text_encoder": {
161
+ "_name_or_path": "google/flan-t5-base",
162
+ "add_cross_attention": false,
163
+ "architectures": [
164
+ "T5ForConditionalGeneration"
165
+ ],
166
+ "bad_words_ids": null,
167
+ "begin_suppress_tokens": null,
168
+ "bos_token_id": null,
169
+ "chunk_size_feed_forward": 0,
170
+ "classifier_dropout": 0.0,
171
+ "cross_attention_hidden_size": null,
172
+ "d_ff": 2048,
173
+ "d_kv": 64,
174
+ "d_model": 768,
175
+ "decoder_start_token_id": 0,
176
+ "dense_act_fn": "gelu_new",
177
+ "diversity_penalty": 0.0,
178
+ "do_sample": false,
179
+ "dropout_rate": 0.1,
180
+ "early_stopping": false,
181
+ "encoder_no_repeat_ngram_size": 0,
182
+ "eos_token_id": 1,
183
+ "exponential_decay_length_penalty": null,
184
+ "feed_forward_proj": "gated-gelu",
185
+ "finetuning_task": null,
186
+ "forced_bos_token_id": null,
187
+ "forced_eos_token_id": null,
188
+ "id2label": {
189
+ "0": "LABEL_0",
190
+ "1": "LABEL_1"
191
+ },
192
+ "initializer_factor": 1.0,
193
+ "is_decoder": false,
194
+ "is_encoder_decoder": true,
195
+ "is_gated_act": true,
196
+ "label2id": {
197
+ "LABEL_0": 0,
198
+ "LABEL_1": 1
199
+ },
200
+ "layer_norm_epsilon": 1e-06,
201
+ "length_penalty": 1.0,
202
+ "max_length": 20,
203
+ "min_length": 0,
204
+ "model_type": "t5",
205
+ "n_positions": 512,
206
+ "no_repeat_ngram_size": 0,
207
+ "num_beam_groups": 1,
208
+ "num_beams": 1,
209
+ "num_decoder_layers": 12,
210
+ "num_heads": 12,
211
+ "num_layers": 12,
212
+ "num_return_sequences": 1,
213
+ "output_attentions": false,
214
+ "output_hidden_states": false,
215
+ "output_past": true,
216
+ "output_scores": false,
217
+ "pad_token_id": 0,
218
+ "prefix": null,
219
+ "problem_type": null,
220
+ "pruned_heads": {},
221
+ "relative_attention_max_distance": 128,
222
+ "relative_attention_num_buckets": 32,
223
+ "remove_invalid_values": false,
224
+ "repetition_penalty": 1.0,
225
+ "return_dict": true,
226
+ "return_dict_in_generate": false,
227
+ "sep_token_id": null,
228
+ "suppress_tokens": null,
229
+ "task_specific_params": {
230
+ "summarization": {
231
+ "early_stopping": true,
232
+ "length_penalty": 2.0,
233
+ "max_length": 200,
234
+ "min_length": 30,
235
+ "no_repeat_ngram_size": 3,
236
+ "num_beams": 4,
237
+ "prefix": "summarize: "
238
+ },
239
+ "translation_en_to_de": {
240
+ "early_stopping": true,
241
+ "max_length": 300,
242
+ "num_beams": 4,
243
+ "prefix": "translate English to German: "
244
+ },
245
+ "translation_en_to_fr": {
246
+ "early_stopping": true,
247
+ "max_length": 300,
248
+ "num_beams": 4,
249
+ "prefix": "translate English to French: "
250
+ },
251
+ "translation_en_to_ro": {
252
+ "early_stopping": true,
253
+ "max_length": 300,
254
+ "num_beams": 4,
255
+ "prefix": "translate English to Romanian: "
256
+ }
257
+ },
258
+ "temperature": 1.0,
259
+ "tf_legacy_loss": false,
260
+ "tie_encoder_decoder": false,
261
+ "tie_word_embeddings": false,
262
+ "tokenizer_class": null,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "torch_dtype": null,
266
+ "torchscript": false,
267
+ "typical_p": 1.0,
268
+ "use_bfloat16": false,
269
+ "use_cache": true,
270
+ "vocab_size": 32128
271
+ },
272
+ "torch_dtype": "float32",
273
+ "transformers_version": "4.38.2",
274
+ "vocab_size": 32128
275
+ }
generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1025,
4
+ "decoder_start_token_id": 1025,
5
+ "do_sample": true,
6
+ "eos_token_id": 1024,
7
+ "guidance_scale": 1.0,
8
+ "max_length": 2580,
9
+ "pad_token_id": 1024,
10
+ "transformers_version": "4.38.2"
11
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:212652a13d02de58494352be5ab5f3bba9335008718d826f2e9e1b922def4b9d
3
+ size 2588215392