Commit
•
db7c3c8
1
Parent(s):
fe17f55
Upload model
Browse files- config.json +64 -226
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,232 +1,70 @@
|
|
1 |
{
|
2 |
-
"_commit_hash": null,
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
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": null,
|
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 |
-
"input_dim": 78,
|
59 |
-
"is_decoder": false,
|
60 |
-
"is_encoder_decoder": true,
|
61 |
-
"label2id": {
|
62 |
-
"LABEL_0": 0,
|
63 |
-
"LABEL_1": 1
|
64 |
-
},
|
65 |
-
"length_penalty": 1.0,
|
66 |
-
"max_length": 20,
|
67 |
-
"max_source_positions": 5000,
|
68 |
-
"min_length": 0,
|
69 |
-
"model_type": "fastspeech2_conformer",
|
70 |
-
"no_repeat_ngram_size": 0,
|
71 |
-
"num_beam_groups": 1,
|
72 |
-
"num_beams": 1,
|
73 |
-
"num_languages": null,
|
74 |
-
"num_mel_bins": 80,
|
75 |
-
"num_return_sequences": 1,
|
76 |
-
"num_speakers": null,
|
77 |
-
"output_attentions": false,
|
78 |
-
"output_hidden_states": false,
|
79 |
-
"output_scores": false,
|
80 |
-
"pad_token_id": null,
|
81 |
-
"pitch_embed_dropout": 0.0,
|
82 |
-
"pitch_embed_kernel_size": 1,
|
83 |
-
"pitch_predictor_channels": 256,
|
84 |
-
"pitch_predictor_dropout": 0.5,
|
85 |
-
"pitch_predictor_kernel_size": 5,
|
86 |
-
"pitch_predictor_layers": 5,
|
87 |
-
"positionwise_conv_kernel_size": 3,
|
88 |
-
"prefix": null,
|
89 |
-
"problem_type": null,
|
90 |
-
"pruned_heads": {},
|
91 |
-
"reduction_factor": 1,
|
92 |
-
"remove_invalid_values": false,
|
93 |
-
"repetition_penalty": 1.0,
|
94 |
-
"return_dict": true,
|
95 |
-
"return_dict_in_generate": false,
|
96 |
-
"sep_token_id": null,
|
97 |
-
"speaker_embed_dim": null,
|
98 |
-
"speaking_speed": 1.0,
|
99 |
-
"speech_decoder_postnet_dropout": 0.5,
|
100 |
-
"speech_decoder_postnet_kernel": 5,
|
101 |
-
"speech_decoder_postnet_layers": 5,
|
102 |
-
"speech_decoder_postnet_units": 256,
|
103 |
-
"stop_gradient_from_energy_predictor": false,
|
104 |
-
"stop_gradient_from_pitch_predictor": true,
|
105 |
-
"suppress_tokens": null,
|
106 |
-
"task_specific_params": null,
|
107 |
-
"temperature": 1.0,
|
108 |
-
"tf_legacy_loss": false,
|
109 |
-
"tie_encoder_decoder": false,
|
110 |
-
"tie_word_embeddings": true,
|
111 |
-
"tokenizer_class": null,
|
112 |
-
"top_k": 50,
|
113 |
-
"top_p": 1.0,
|
114 |
-
"torch_dtype": null,
|
115 |
-
"torchscript": false,
|
116 |
-
"transformers_version": "4.32.0.dev0",
|
117 |
-
"typical_p": 1.0,
|
118 |
-
"use_bfloat16": false,
|
119 |
-
"use_cnn_in_conformer": true,
|
120 |
-
"use_macaron_style_in_conformer": true,
|
121 |
-
"use_masking": true,
|
122 |
-
"use_weighted_masking": false,
|
123 |
-
"vocab_size": 78
|
124 |
},
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"cross_attention_hidden_size": null,
|
137 |
-
"decoder_start_token_id": null,
|
138 |
-
"diversity_penalty": 0.0,
|
139 |
-
"do_sample": false,
|
140 |
-
"early_stopping": false,
|
141 |
-
"encoder_no_repeat_ngram_size": 0,
|
142 |
-
"eos_token_id": null,
|
143 |
-
"exponential_decay_length_penalty": null,
|
144 |
-
"finetuning_task": null,
|
145 |
-
"forced_bos_token_id": null,
|
146 |
-
"forced_eos_token_id": null,
|
147 |
-
"id2label": {
|
148 |
-
"0": "LABEL_0",
|
149 |
-
"1": "LABEL_1"
|
150 |
-
},
|
151 |
-
"initializer_range": 0.01,
|
152 |
-
"is_decoder": false,
|
153 |
-
"is_encoder_decoder": false,
|
154 |
-
"label2id": {
|
155 |
-
"LABEL_0": 0,
|
156 |
-
"LABEL_1": 1
|
157 |
-
},
|
158 |
-
"leaky_relu_slope": 0.1,
|
159 |
-
"length_penalty": 1.0,
|
160 |
-
"max_length": 20,
|
161 |
-
"min_length": 0,
|
162 |
-
"model_in_dim": 80,
|
163 |
-
"model_type": "hifigan",
|
164 |
-
"no_repeat_ngram_size": 0,
|
165 |
"normalize_before": false,
|
166 |
-
"
|
167 |
-
"
|
168 |
-
|
169 |
-
|
170 |
-
|
171 |
-
|
172 |
-
|
173 |
-
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
-
|
178 |
-
|
179 |
-
|
180 |
-
|
181 |
-
|
182 |
-
|
183 |
-
|
184 |
-
|
185 |
-
|
186 |
-
|
187 |
-
|
188 |
-
|
189 |
-
|
190 |
-
|
191 |
-
|
192 |
-
|
193 |
-
|
194 |
-
|
195 |
-
|
196 |
-
|
197 |
-
|
198 |
-
|
199 |
-
|
200 |
-
|
201 |
-
|
202 |
-
|
203 |
-
|
204 |
-
|
205 |
-
|
206 |
-
|
207 |
-
|
208 |
-
"tie_encoder_decoder": false,
|
209 |
-
"tie_word_embeddings": true,
|
210 |
-
"tokenizer_class": null,
|
211 |
-
"top_k": 50,
|
212 |
-
"top_p": 1.0,
|
213 |
-
"torch_dtype": null,
|
214 |
-
"torchscript": false,
|
215 |
-
"transformers_version": "4.32.0.dev0",
|
216 |
-
"typical_p": 1.0,
|
217 |
-
"upsample_initial_channel": 512,
|
218 |
-
"upsample_kernel_sizes": [
|
219 |
-
16,
|
220 |
-
16,
|
221 |
-
4,
|
222 |
-
4
|
223 |
-
],
|
224 |
-
"upsample_rates": [
|
225 |
-
8,
|
226 |
-
8,
|
227 |
-
2,
|
228 |
-
2
|
229 |
-
],
|
230 |
-
"use_bfloat16": false
|
231 |
-
}
|
232 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
+
"FastSpeech2ConformerModel"
|
4 |
],
|
5 |
+
"decoder_config": {
|
6 |
+
"attention_dropout_rate": 0.2,
|
7 |
+
"concat_after": false,
|
8 |
+
"dropout_rate": 0.2,
|
9 |
+
"kernel_size": 31,
|
10 |
+
"layers": 4,
|
11 |
+
"linear_units": 1536,
|
12 |
+
"normalize_before": false,
|
13 |
+
"num_attention_heads": 2,
|
14 |
+
"positional_dropout_rate": 0.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
},
|
16 |
+
"duration_predictor_channels": 256,
|
17 |
+
"duration_predictor_dropout_rate": 0.2,
|
18 |
+
"duration_predictor_kernel_size": 3,
|
19 |
+
"duration_predictor_layers": 2,
|
20 |
+
"encoder_config": {
|
21 |
+
"attention_dropout_rate": 0.2,
|
22 |
+
"concat_after": false,
|
23 |
+
"dropout_rate": 0.2,
|
24 |
+
"kernel_size": 7,
|
25 |
+
"layers": 4,
|
26 |
+
"linear_units": 1536,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
"normalize_before": false,
|
28 |
+
"num_attention_heads": 2,
|
29 |
+
"positional_dropout_rate": 0.2
|
30 |
+
},
|
31 |
+
"encoder_layers": 4,
|
32 |
+
"encoder_num_attention_heads": 2,
|
33 |
+
"energy_embed_dropout": 0.0,
|
34 |
+
"energy_embed_kernel_size": 1,
|
35 |
+
"energy_predictor_channels": 256,
|
36 |
+
"energy_predictor_dropout": 0.5,
|
37 |
+
"energy_predictor_kernel_size": 3,
|
38 |
+
"energy_predictor_layers": 2,
|
39 |
+
"hidden_size": 384,
|
40 |
+
"input_dim": 78,
|
41 |
+
"is_encoder_decoder": true,
|
42 |
+
"max_source_positions": 5000,
|
43 |
+
"model_type": "fastspeech2_conformer",
|
44 |
+
"num_languages": null,
|
45 |
+
"num_mel_bins": 80,
|
46 |
+
"num_speakers": null,
|
47 |
+
"pitch_embed_dropout": 0.0,
|
48 |
+
"pitch_embed_kernel_size": 1,
|
49 |
+
"pitch_predictor_channels": 256,
|
50 |
+
"pitch_predictor_dropout": 0.5,
|
51 |
+
"pitch_predictor_kernel_size": 5,
|
52 |
+
"pitch_predictor_layers": 5,
|
53 |
+
"positionwise_conv_kernel_size": 3,
|
54 |
+
"reduction_factor": 1,
|
55 |
+
"speaker_embed_dim": null,
|
56 |
+
"speaking_speed": 1.0,
|
57 |
+
"speech_decoder_postnet_dropout": 0.5,
|
58 |
+
"speech_decoder_postnet_kernel": 5,
|
59 |
+
"speech_decoder_postnet_layers": 5,
|
60 |
+
"speech_decoder_postnet_units": 256,
|
61 |
+
"stop_gradient_from_energy_predictor": false,
|
62 |
+
"stop_gradient_from_pitch_predictor": true,
|
63 |
+
"torch_dtype": "float32",
|
64 |
+
"transformers_version": "4.33.0.dev0",
|
65 |
+
"use_cnn_in_conformer": true,
|
66 |
+
"use_macaron_style_in_conformer": true,
|
67 |
+
"use_masking": true,
|
68 |
+
"use_weighted_masking": false,
|
69 |
+
"vocab_size": 78
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fa4096f1c4ce019198a7ec8054a7828916bc94b6c6cb968d7723d5a4b808b7a8
|
3 |
+
size 281215241
|