drewThomasson
commited on
Commit
•
27fcdf5
1
Parent(s):
0d8f467
Upload 8 files
Browse files- tts_models/.DS_Store +0 -0
- tts_models/voice_conversion_models--multilingual--vctk--freevc24/.DS_Store +0 -0
- tts_models/voice_conversion_models--multilingual--vctk--freevc24/._config.json +0 -0
- tts_models/voice_conversion_models--multilingual--vctk--freevc24/._model.pth +3 -0
- tts_models/voice_conversion_models--multilingual--vctk--freevc24/._voice_conversion_models--multilingual--vctk--freevc24 +0 -0
- tts_models/voice_conversion_models--multilingual--vctk--freevc24/config.json +204 -0
- tts_models/voice_conversion_models--multilingual--vctk--freevc24/model.pth +3 -0
- tts_models/wavlm/WavLM-Large.pt +3 -0
tts_models/.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
tts_models/voice_conversion_models--multilingual--vctk--freevc24/.DS_Store
ADDED
Binary file (6.15 kB). View file
|
|
tts_models/voice_conversion_models--multilingual--vctk--freevc24/._config.json
ADDED
Binary file (386 Bytes). View file
|
|
tts_models/voice_conversion_models--multilingual--vctk--freevc24/._model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fa468ed77a9726751b4d321242e069c77dbcd8ecb2e30a212dc0f38f69b852a
|
3 |
+
size 230
|
tts_models/voice_conversion_models--multilingual--vctk--freevc24/._voice_conversion_models--multilingual--vctk--freevc24
ADDED
Binary file (330 Bytes). View file
|
|
tts_models/voice_conversion_models--multilingual--vctk--freevc24/config.json
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"output_path": "output",
|
3 |
+
"logger_uri": null,
|
4 |
+
"run_name": "run",
|
5 |
+
"project_name": null,
|
6 |
+
"run_description": "\ud83d\udc38Coqui trainer run.",
|
7 |
+
"print_step": 25,
|
8 |
+
"plot_step": 100,
|
9 |
+
"model_param_stats": false,
|
10 |
+
"wandb_entity": null,
|
11 |
+
"dashboard_logger": "tensorboard",
|
12 |
+
"log_model_step": null,
|
13 |
+
"save_step": 10000,
|
14 |
+
"save_n_checkpoints": 5,
|
15 |
+
"save_checkpoints": true,
|
16 |
+
"save_all_best": false,
|
17 |
+
"save_best_after": 10000,
|
18 |
+
"target_loss": null,
|
19 |
+
"print_eval": false,
|
20 |
+
"test_delay_epochs": 0,
|
21 |
+
"run_eval": true,
|
22 |
+
"run_eval_steps": null,
|
23 |
+
"distributed_backend": "nccl",
|
24 |
+
"distributed_url": "tcp://localhost:54321",
|
25 |
+
"mixed_precision": false,
|
26 |
+
"epochs": 1000,
|
27 |
+
"batch_size": 32,
|
28 |
+
"eval_batch_size": 16,
|
29 |
+
"grad_clip": [
|
30 |
+
1000,
|
31 |
+
1000
|
32 |
+
],
|
33 |
+
"scheduler_after_epoch": true,
|
34 |
+
"lr": 0.001,
|
35 |
+
"optimizer": "AdamW",
|
36 |
+
"optimizer_params": {
|
37 |
+
"betas": [
|
38 |
+
0.8,
|
39 |
+
0.99
|
40 |
+
],
|
41 |
+
"eps": 1e-09,
|
42 |
+
"weight_decay": 0.01
|
43 |
+
},
|
44 |
+
"lr_scheduler": null,
|
45 |
+
"lr_scheduler_params": {},
|
46 |
+
"use_grad_scaler": false,
|
47 |
+
"cudnn_enable": true,
|
48 |
+
"cudnn_deterministic": false,
|
49 |
+
"cudnn_benchmark": false,
|
50 |
+
"training_seed": 54321,
|
51 |
+
"model": "freevc",
|
52 |
+
"num_loader_workers": 0,
|
53 |
+
"num_eval_loader_workers": 0,
|
54 |
+
"use_noise_augment": false,
|
55 |
+
"audio": {
|
56 |
+
"max_wav_value": 32768.0,
|
57 |
+
"input_sample_rate": 16000,
|
58 |
+
"output_sample_rate": 24000,
|
59 |
+
"filter_length": 1280,
|
60 |
+
"hop_length": 320,
|
61 |
+
"win_length": 1280,
|
62 |
+
"n_mel_channels": 80,
|
63 |
+
"mel_fmin": 0.0,
|
64 |
+
"mel_fmax": null
|
65 |
+
},
|
66 |
+
"batch_group_size": 0,
|
67 |
+
"loss_masking": null,
|
68 |
+
"min_audio_len": 1,
|
69 |
+
"max_audio_len": Infinity,
|
70 |
+
"min_text_len": 1,
|
71 |
+
"max_text_len": Infinity,
|
72 |
+
"compute_f0": false,
|
73 |
+
"compute_energy": false,
|
74 |
+
"compute_linear_spec": true,
|
75 |
+
"precompute_num_workers": 0,
|
76 |
+
"start_by_longest": false,
|
77 |
+
"shuffle": false,
|
78 |
+
"drop_last": false,
|
79 |
+
"datasets": [
|
80 |
+
{
|
81 |
+
"formatter": "",
|
82 |
+
"dataset_name": "",
|
83 |
+
"path": "",
|
84 |
+
"meta_file_train": "",
|
85 |
+
"ignored_speakers": null,
|
86 |
+
"language": "",
|
87 |
+
"phonemizer": "",
|
88 |
+
"meta_file_val": "",
|
89 |
+
"meta_file_attn_mask": ""
|
90 |
+
}
|
91 |
+
],
|
92 |
+
"test_sentences": [
|
93 |
+
[
|
94 |
+
"It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent."
|
95 |
+
],
|
96 |
+
[
|
97 |
+
"Be a voice, not an echo."
|
98 |
+
],
|
99 |
+
[
|
100 |
+
"I'm sorry Dave. I'm afraid I can't do that."
|
101 |
+
],
|
102 |
+
[
|
103 |
+
"This cake is great. It's so delicious and moist."
|
104 |
+
],
|
105 |
+
[
|
106 |
+
"Prior to November 22, 1963."
|
107 |
+
]
|
108 |
+
],
|
109 |
+
"eval_split_max_size": null,
|
110 |
+
"eval_split_size": 0.01,
|
111 |
+
"use_speaker_weighted_sampler": false,
|
112 |
+
"speaker_weighted_sampler_alpha": 1.0,
|
113 |
+
"use_language_weighted_sampler": false,
|
114 |
+
"language_weighted_sampler_alpha": 1.0,
|
115 |
+
"use_length_weighted_sampler": false,
|
116 |
+
"length_weighted_sampler_alpha": 1.0,
|
117 |
+
"model_args": {
|
118 |
+
"spec_channels": 641,
|
119 |
+
"inter_channels": 192,
|
120 |
+
"hidden_channels": 192,
|
121 |
+
"filter_channels": 768,
|
122 |
+
"n_heads": 2,
|
123 |
+
"n_layers": 6,
|
124 |
+
"kernel_size": 3,
|
125 |
+
"p_dropout": 0.1,
|
126 |
+
"resblock": "1",
|
127 |
+
"resblock_kernel_sizes": [
|
128 |
+
3,
|
129 |
+
7,
|
130 |
+
11
|
131 |
+
],
|
132 |
+
"resblock_dilation_sizes": [
|
133 |
+
[
|
134 |
+
1,
|
135 |
+
3,
|
136 |
+
5
|
137 |
+
],
|
138 |
+
[
|
139 |
+
1,
|
140 |
+
3,
|
141 |
+
5
|
142 |
+
],
|
143 |
+
[
|
144 |
+
1,
|
145 |
+
3,
|
146 |
+
5
|
147 |
+
]
|
148 |
+
],
|
149 |
+
"upsample_rates": [
|
150 |
+
10,
|
151 |
+
6,
|
152 |
+
4,
|
153 |
+
2
|
154 |
+
],
|
155 |
+
"upsample_initial_channel": 512,
|
156 |
+
"upsample_kernel_sizes": [
|
157 |
+
16,
|
158 |
+
16,
|
159 |
+
4,
|
160 |
+
4
|
161 |
+
],
|
162 |
+
"n_layers_q": 3,
|
163 |
+
"use_spectral_norm": false,
|
164 |
+
"gin_channels": 256,
|
165 |
+
"ssl_dim": 1024,
|
166 |
+
"use_spk": true,
|
167 |
+
"num_spks": 0,
|
168 |
+
"segment_size": 8960
|
169 |
+
},
|
170 |
+
"lr_gen": 0.0002,
|
171 |
+
"lr_disc": 0.0002,
|
172 |
+
"lr_scheduler_gen": "ExponentialLR",
|
173 |
+
"lr_scheduler_gen_params": {
|
174 |
+
"gamma": 0.999875,
|
175 |
+
"last_epoch": -1
|
176 |
+
},
|
177 |
+
"lr_scheduler_disc": "ExponentialLR",
|
178 |
+
"lr_scheduler_disc_params": {
|
179 |
+
"gamma": 0.999875,
|
180 |
+
"last_epoch": -1
|
181 |
+
},
|
182 |
+
"kl_loss_alpha": 1.0,
|
183 |
+
"disc_loss_alpha": 1.0,
|
184 |
+
"gen_loss_alpha": 1.0,
|
185 |
+
"feat_loss_alpha": 1.0,
|
186 |
+
"mel_loss_alpha": 45.0,
|
187 |
+
"dur_loss_alpha": 1.0,
|
188 |
+
"speaker_encoder_loss_alpha": 1.0,
|
189 |
+
"return_wav": true,
|
190 |
+
"use_weighted_sampler": false,
|
191 |
+
"weighted_sampler_attrs": {},
|
192 |
+
"weighted_sampler_multipliers": {},
|
193 |
+
"r": 1,
|
194 |
+
"add_blank": true,
|
195 |
+
"num_speakers": 0,
|
196 |
+
"use_speaker_embedding": false,
|
197 |
+
"speakers_file": null,
|
198 |
+
"speaker_embedding_channels": 256,
|
199 |
+
"language_ids_file": null,
|
200 |
+
"use_language_embedding": false,
|
201 |
+
"use_d_vector_file": false,
|
202 |
+
"d_vector_file": null,
|
203 |
+
"d_vector_dim": null
|
204 |
+
}
|
tts_models/voice_conversion_models--multilingual--vctk--freevc24/model.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18d4ce44e7c803d675be1984b174e0f7bf05ce937419f19a818877e83f197007
|
3 |
+
size 1425242419
|
tts_models/wavlm/WavLM-Large.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6fb4b3c3e6aa567f0a997b30855859cb81528ee8078802af439f7b2da0bf100f
|
3 |
+
size 1261965425
|