Hugging Face's logo

espnet
/
fastspeech2_conformer

Text-to-Audio
Transformers
PyTorch
English
fastspeech2_conformer
audio
Inference Endpoints
Model card Files Community
1
connor-henderson commited on
Commit
0fab2df
·
1 Parent(s): ecc8dc1

Upload FastSpeech2ConformerWithHifiGan

Browse files
Files changed (2) hide show
  1. config.json +223 -41
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,48 +1,230 @@
1
  {
 
2
  "architectures": [
3
- "FastSpeech2ConformerHifiGan"
4
  ],
5
- "initializer_range": 0.01,
6
- "leaky_relu_slope": 0.1,
7
- "model_in_dim": 80,
8
- "model_type": "hifigan",
9
- "normalize_before": false,
10
- "resblock_dilation_sizes": [
11
- [
12
- 1,
13
- 3,
14
- 5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ],
16
- [
17
- 1,
18
  3,
19
- 5
 
20
  ],
21
- [
22
- 1,
23
- 3,
24
- 5
25
- ]
26
- ],
27
- "resblock_kernel_sizes": [
28
- 3,
29
- 7,
30
- 11
31
- ],
32
- "sampling_rate": 22050,
33
- "torch_dtype": "float32",
34
- "transformers_version": "4.31.0.dev0",
35
- "upsample_initial_channel": 512,
36
- "upsample_kernel_sizes": [
37
- 16,
38
- 16,
39
- 4,
40
- 4
41
- ],
42
- "upsample_rates": [
43
- 8,
44
- 8,
45
- 2,
46
- 2
47
- ]
 
 
 
 
48
  }
 
1
  {
2
+ "_commit_hash": null,
3
  "architectures": [
4
+ "FastSpeech2ConformerWithHifiGan"
5
  ],
6
+ "model_config": {
7
+ "_name_or_path": "",
8
+ "add_cross_attention": false,
9
+ "architectures": null,
10
+ "bad_words_ids": null,
11
+ "begin_suppress_tokens": null,
12
+ "bos_token_id": 77,
13
+ "chunk_size_feed_forward": 0,
14
+ "cross_attention_hidden_size": null,
15
+ "decoder_attention_dropout_rate": 0.2,
16
+ "decoder_concat_after": false,
17
+ "decoder_dropout_rate": 0.2,
18
+ "decoder_kernel_size": 31,
19
+ "decoder_layers": 4,
20
+ "decoder_linear_units": 1536,
21
+ "decoder_normalize_before": false,
22
+ "decoder_num_attention_heads": 2,
23
+ "decoder_positional_dropout_rate": 0.2,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "duration_predictor_channels": 256,
28
+ "duration_predictor_dropout_rate": 0.2,
29
+ "duration_predictor_kernel_size": 3,
30
+ "duration_predictor_layers": 2,
31
+ "early_stopping": false,
32
+ "encoder_attention_dropout_rate": 0.2,
33
+ "encoder_concat_after": false,
34
+ "encoder_dropout_rate": 0.2,
35
+ "encoder_kernel_size": 7,
36
+ "encoder_layers": 4,
37
+ "encoder_linear_units": 1536,
38
+ "encoder_no_repeat_ngram_size": 0,
39
+ "encoder_normalize_before": false,
40
+ "encoder_num_attention_heads": 2,
41
+ "encoder_positional_dropout_rate": 0.2,
42
+ "energy_embed_dropout": 0.0,
43
+ "energy_embed_kernel_size": 1,
44
+ "energy_predictor_channels": 256,
45
+ "energy_predictor_dropout": 0.5,
46
+ "energy_predictor_kernel_size": 3,
47
+ "energy_predictor_layers": 2,
48
+ "eos_token_id": 77,
49
+ "exponential_decay_length_penalty": null,
50
+ "finetuning_task": null,
51
+ "forced_bos_token_id": null,
52
+ "forced_eos_token_id": null,
53
+ "hidden_size": 384,
54
+ "id2label": {
55
+ "0": "LABEL_0",
56
+ "1": "LABEL_1"
57
+ },
58
+ "is_decoder": false,
59
+ "is_encoder_decoder": true,
60
+ "label2id": {
61
+ "LABEL_0": 0,
62
+ "LABEL_1": 1
63
+ },
64
+ "length_penalty": 1.0,
65
+ "max_length": 20,
66
+ "max_source_positions": 5000,
67
+ "min_length": 0,
68
+ "model_type": "fastspeech2_conformer",
69
+ "no_repeat_ngram_size": 0,
70
+ "num_beam_groups": 1,
71
+ "num_beams": 1,
72
+ "num_languages": null,
73
+ "num_mel_bins": 80,
74
+ "num_return_sequences": 1,
75
+ "num_speakers": null,
76
+ "output_attentions": false,
77
+ "output_hidden_states": false,
78
+ "output_scores": false,
79
+ "pad_token_id": 0,
80
+ "pitch_embed_dropout": 0.0,
81
+ "pitch_embed_kernel_size": 1,
82
+ "pitch_predictor_channels": 256,
83
+ "pitch_predictor_dropout": 0.5,
84
+ "pitch_predictor_kernel_size": 5,
85
+ "pitch_predictor_layers": 5,
86
+ "positionwise_conv_kernel_size": 3,
87
+ "prefix": null,
88
+ "problem_type": null,
89
+ "pruned_heads": {},
90
+ "reduction_factor": 1,
91
+ "remove_invalid_values": false,
92
+ "repetition_penalty": 1.0,
93
+ "return_dict": true,
94
+ "return_dict_in_generate": false,
95
+ "sep_token_id": null,
96
+ "speaker_embed_dim": null,
97
+ "speaking_speed": 1.0,
98
+ "speech_decoder_postnet_dropout": 0.5,
99
+ "speech_decoder_postnet_kernel": 5,
100
+ "speech_decoder_postnet_layers": 5,
101
+ "speech_decoder_postnet_units": 256,
102
+ "stop_gradient_from_energy_predictor": false,
103
+ "stop_gradient_from_pitch_predictor": true,
104
+ "suppress_tokens": null,
105
+ "task_specific_params": null,
106
+ "temperature": 1.0,
107
+ "tf_legacy_loss": false,
108
+ "tie_encoder_decoder": false,
109
+ "tie_word_embeddings": true,
110
+ "tokenizer_class": null,
111
+ "top_k": 50,
112
+ "top_p": 1.0,
113
+ "torch_dtype": null,
114
+ "torchscript": false,
115
+ "transformers_version": "4.31.0.dev0",
116
+ "typical_p": 1.0,
117
+ "use_bfloat16": false,
118
+ "use_cnn_in_conformer": true,
119
+ "use_macaron_style_in_conformer": true,
120
+ "use_masking": true,
121
+ "use_weighted_masking": false,
122
+ "vocab_size": 78
123
+ },
124
+ "model_type": "fastspeech2_conformer_with_hifigan",
125
+ "torch_dtype": "float32",
126
+ "transformers_version": null,
127
+ "vocoder_config": {
128
+ "_name_or_path": "",
129
+ "add_cross_attention": false,
130
+ "architectures": null,
131
+ "bad_words_ids": null,
132
+ "begin_suppress_tokens": null,
133
+ "bos_token_id": null,
134
+ "chunk_size_feed_forward": 0,
135
+ "cross_attention_hidden_size": null,
136
+ "decoder_start_token_id": null,
137
+ "diversity_penalty": 0.0,
138
+ "do_sample": false,
139
+ "early_stopping": false,
140
+ "encoder_no_repeat_ngram_size": 0,
141
+ "eos_token_id": null,
142
+ "exponential_decay_length_penalty": null,
143
+ "finetuning_task": null,
144
+ "forced_bos_token_id": null,
145
+ "forced_eos_token_id": null,
146
+ "id2label": {
147
+ "0": "LABEL_0",
148
+ "1": "LABEL_1"
149
+ },
150
+ "initializer_range": 0.01,
151
+ "is_decoder": false,
152
+ "is_encoder_decoder": false,
153
+ "label2id": {
154
+ "LABEL_0": 0,
155
+ "LABEL_1": 1
156
+ },
157
+ "leaky_relu_slope": 0.1,
158
+ "length_penalty": 1.0,
159
+ "max_length": 20,
160
+ "min_length": 0,
161
+ "model_in_dim": 80,
162
+ "model_type": "hifigan",
163
+ "no_repeat_ngram_size": 0,
164
+ "normalize_before": true,
165
+ "num_beam_groups": 1,
166
+ "num_beams": 1,
167
+ "num_return_sequences": 1,
168
+ "output_attentions": false,
169
+ "output_hidden_states": false,
170
+ "output_scores": false,
171
+ "pad_token_id": null,
172
+ "prefix": null,
173
+ "problem_type": null,
174
+ "pruned_heads": {},
175
+ "remove_invalid_values": false,
176
+ "repetition_penalty": 1.0,
177
+ "resblock_dilation_sizes": [
178
+ [
179
+ 1,
180
+ 3,
181
+ 5
182
+ ],
183
+ [
184
+ 1,
185
+ 3,
186
+ 5
187
+ ],
188
+ [
189
+ 1,
190
+ 3,
191
+ 5
192
+ ]
193
  ],
194
+ "resblock_kernel_sizes": [
 
195
  3,
196
+ 7,
197
+ 11
198
  ],
199
+ "return_dict": true,
200
+ "return_dict_in_generate": false,
201
+ "sep_token_id": null,
202
+ "suppress_tokens": null,
203
+ "task_specific_params": null,
204
+ "temperature": 1.0,
205
+ "tf_legacy_loss": false,
206
+ "tie_encoder_decoder": false,
207
+ "tie_word_embeddings": true,
208
+ "tokenizer_class": null,
209
+ "top_k": 50,
210
+ "top_p": 1.0,
211
+ "torch_dtype": null,
212
+ "torchscript": false,
213
+ "transformers_version": "4.31.0.dev0",
214
+ "typical_p": 1.0,
215
+ "upsample_initial_channel": 512,
216
+ "upsample_kernel_sizes": [
217
+ 16,
218
+ 16,
219
+ 4,
220
+ 4
221
+ ],
222
+ "upsample_rates": [
223
+ 8,
224
+ 8,
225
+ 2,
226
+ 2
227
+ ],
228
+ "use_bfloat16": false
229
+ }
230
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b9bc64b2dcd2a463a2bb6bcf89c9482015fe8e75cbabee59e314ae7cad1cb47
3
- size 55751869
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:960639849085a9ee2d41e6bb9a8dcdf862768375fbfaeb788124502b54846ddd
3
+ size 336970809