Hugging Face's logo

eeeebbb2
/
empathetic-speech-v4

Safetensors
parler_tts
Model card Files Community
eeeebbb2 commited on
Commit
9cde5a5
·
verified ·
1 Parent(s): 3de1ee2

Upload model file: config.json

Browse files
Files changed (1) hide show
  1. config.json +252 -0
config.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "ParlerTTSForConditionalGeneration"
4
+ ],
5
+ "audio_encoder": {
6
+ "_name_or_path": "parler-tts/dac_44khZ_8kbps",
7
+ "add_cross_attention": false,
8
+ "architectures": [
9
+ "DACModel"
10
+ ],
11
+ "bad_words_ids": null,
12
+ "begin_suppress_tokens": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "codebook_size": 1024,
16
+ "cross_attention_hidden_size": null,
17
+ "decoder_start_token_id": null,
18
+ "diversity_penalty": 0.0,
19
+ "do_sample": false,
20
+ "early_stopping": false,
21
+ "encoder_no_repeat_ngram_size": 0,
22
+ "eos_token_id": null,
23
+ "exponential_decay_length_penalty": null,
24
+ "finetuning_task": null,
25
+ "forced_bos_token_id": null,
26
+ "forced_eos_token_id": null,
27
+ "frame_rate": 86,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1"
31
+ },
32
+ "is_decoder": false,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "latent_dim": 1024,
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "min_length": 0,
42
+ "model_bitrate": 8,
43
+ "model_type": "dac",
44
+ "no_repeat_ngram_size": 0,
45
+ "num_beam_groups": 1,
46
+ "num_beams": 1,
47
+ "num_codebooks": 9,
48
+ "num_return_sequences": 1,
49
+ "output_attentions": false,
50
+ "output_hidden_states": false,
51
+ "output_scores": false,
52
+ "pad_token_id": null,
53
+ "prefix": null,
54
+ "problem_type": null,
55
+ "pruned_heads": {},
56
+ "remove_invalid_values": false,
57
+ "repetition_penalty": 1.0,
58
+ "return_dict": true,
59
+ "return_dict_in_generate": false,
60
+ "sampling_rate": 44100,
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
+ "activation_dropout": 0.0,
78
+ "activation_function": "gelu",
79
+ "add_cross_attention": true,
80
+ "architectures": [
81
+ "ParlerTTSForCausalLM"
82
+ ],
83
+ "attention_dropout": 0.0,
84
+ "bad_words_ids": null,
85
+ "begin_suppress_tokens": null,
86
+ "bos_token_id": 1025,
87
+ "chunk_size_feed_forward": 0,
88
+ "cross_attention_hidden_size": null,
89
+ "cross_attention_implementation_strategy": 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": "parler_tts_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_cross_attention_key_value_heads": 16,
126
+ "num_hidden_layers": 24,
127
+ "num_key_value_heads": 16,
128
+ "num_return_sequences": 1,
129
+ "output_attentions": false,
130
+ "output_hidden_states": false,
131
+ "output_scores": false,
132
+ "pad_token_id": 1024,
133
+ "prefix": null,
134
+ "problem_type": null,
135
+ "pruned_heads": {},
136
+ "remove_invalid_values": false,
137
+ "repetition_penalty": 1.0,
138
+ "return_dict": true,
139
+ "return_dict_in_generate": false,
140
+ "rope_embeddings": false,
141
+ "rope_theta": 10000.0,
142
+ "scale_embedding": false,
143
+ "sep_token_id": null,
144
+ "suppress_tokens": null,
145
+ "task_specific_params": null,
146
+ "temperature": 1.0,
147
+ "tf_legacy_loss": false,
148
+ "tie_encoder_decoder": false,
149
+ "tie_word_embeddings": false,
150
+ "tokenizer_class": null,
151
+ "top_k": 50,
152
+ "top_p": 1.0,
153
+ "torch_dtype": "float32",
154
+ "torchscript": false,
155
+ "typical_p": 1.0,
156
+ "use_bfloat16": false,
157
+ "use_cache": true,
158
+ "vocab_size": 1088
159
+ },
160
+ "decoder_start_token_id": 1025,
161
+ "is_encoder_decoder": true,
162
+ "model_type": "parler_tts",
163
+ "pad_token_id": 1024,
164
+ "prompt_cross_attention": false,
165
+ "text_encoder": {
166
+ "_name_or_path": "google/flan-t5-large",
167
+ "add_cross_attention": false,
168
+ "architectures": [
169
+ "T5ForConditionalGeneration"
170
+ ],
171
+ "bad_words_ids": null,
172
+ "begin_suppress_tokens": null,
173
+ "bos_token_id": null,
174
+ "chunk_size_feed_forward": 0,
175
+ "classifier_dropout": 0.0,
176
+ "cross_attention_hidden_size": null,
177
+ "d_ff": 2816,
178
+ "d_kv": 64,
179
+ "d_model": 1024,
180
+ "decoder_start_token_id": 0,
181
+ "dense_act_fn": "gelu_new",
182
+ "diversity_penalty": 0.0,
183
+ "do_sample": false,
184
+ "dropout_rate": 0.1,
185
+ "early_stopping": false,
186
+ "encoder_no_repeat_ngram_size": 0,
187
+ "eos_token_id": 1,
188
+ "exponential_decay_length_penalty": null,
189
+ "feed_forward_proj": "gated-gelu",
190
+ "finetuning_task": null,
191
+ "forced_bos_token_id": null,
192
+ "forced_eos_token_id": null,
193
+ "id2label": {
194
+ "0": "LABEL_0",
195
+ "1": "LABEL_1"
196
+ },
197
+ "initializer_factor": 1.0,
198
+ "is_decoder": false,
199
+ "is_encoder_decoder": true,
200
+ "is_gated_act": true,
201
+ "label2id": {
202
+ "LABEL_0": 0,
203
+ "LABEL_1": 1
204
+ },
205
+ "layer_norm_epsilon": 1e-06,
206
+ "length_penalty": 1.0,
207
+ "max_length": 20,
208
+ "min_length": 0,
209
+ "model_type": "t5",
210
+ "n_positions": 512,
211
+ "no_repeat_ngram_size": 0,
212
+ "num_beam_groups": 1,
213
+ "num_beams": 1,
214
+ "num_decoder_layers": 24,
215
+ "num_heads": 16,
216
+ "num_layers": 24,
217
+ "num_return_sequences": 1,
218
+ "output_attentions": false,
219
+ "output_hidden_states": false,
220
+ "output_past": true,
221
+ "output_scores": false,
222
+ "pad_token_id": 0,
223
+ "prefix": null,
224
+ "problem_type": null,
225
+ "pruned_heads": {},
226
+ "relative_attention_max_distance": 128,
227
+ "relative_attention_num_buckets": 32,
228
+ "remove_invalid_values": false,
229
+ "repetition_penalty": 1.0,
230
+ "return_dict": true,
231
+ "return_dict_in_generate": false,
232
+ "sep_token_id": null,
233
+ "suppress_tokens": null,
234
+ "task_specific_params": null,
235
+ "temperature": 1.0,
236
+ "tf_legacy_loss": false,
237
+ "tie_encoder_decoder": false,
238
+ "tie_word_embeddings": false,
239
+ "tokenizer_class": null,
240
+ "top_k": 50,
241
+ "top_p": 1.0,
242
+ "torch_dtype": null,
243
+ "torchscript": false,
244
+ "typical_p": 1.0,
245
+ "use_bfloat16": false,
246
+ "use_cache": true,
247
+ "vocab_size": 32128
248
+ },
249
+ "torch_dtype": "float32",
250
+ "transformers_version": "4.43.3",
251
+ "vocab_size": 32128
252
+ }