youmebangbang commited on
Commit
e4fc405
1 Parent(s): 87dc03d

Upload 7 files

Browse files
adam_carolla_checkpoint_1360000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3837f421d7dc4cca7ee0afe85e9a3fd9baac1f0bbd7e982e58816dcea5012c5
3
+ size 997870725
config.json ADDED
@@ -0,0 +1,266 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "/home/zombie/TTS/recipes/ljspeech/vits_tts",
3
+ "logger_uri": null,
4
+ "run_name": "attenborough50000ep_ljspeech",
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": true,
20
+ "test_delay_epochs": -1,
21
+ "run_eval": true,
22
+ "run_eval_steps": null,
23
+ "distributed_backend": "nccl",
24
+ "distributed_url": "tcp://localhost:54321",
25
+ "mixed_precision": true,
26
+ "epochs": 50000,
27
+ "batch_size": 100,
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": "vits",
52
+ "num_loader_workers": 8,
53
+ "num_eval_loader_workers": 4,
54
+ "use_noise_augment": false,
55
+ "audio": {
56
+ "fft_size": 1024,
57
+ "sample_rate": 22050,
58
+ "win_length": 1024,
59
+ "hop_length": 256,
60
+ "num_mels": 80,
61
+ "mel_fmin": 0,
62
+ "mel_fmax": null
63
+ },
64
+ "use_phonemes": true,
65
+ "phonemizer": "espeak",
66
+ "phoneme_language": "en-us",
67
+ "compute_input_seq_cache": true,
68
+ "text_cleaner": "english_cleaners",
69
+ "enable_eos_bos_chars": false,
70
+ "test_sentences_file": "",
71
+ "phoneme_cache_path": "/home/zombie/TTS/recipes/ljspeech/vits_tts/phoneme_cache",
72
+ "characters": {
73
+ "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
74
+ "vocab_dict": null,
75
+ "pad": "<PAD>",
76
+ "eos": "<EOS>",
77
+ "bos": "<BOS>",
78
+ "blank": "<BLNK>",
79
+ "characters": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u02b2\u025a\u02de\u026b",
80
+ "punctuations": "!'(),-.:;? ",
81
+ "phonemes": null,
82
+ "is_unique": false,
83
+ "is_sorted": true
84
+ },
85
+ "add_blank": true,
86
+ "batch_group_size": 5,
87
+ "loss_masking": null,
88
+ "min_audio_len": 1,
89
+ "max_audio_len": Infinity,
90
+ "min_text_len": 1,
91
+ "max_text_len": Infinity,
92
+ "compute_f0": false,
93
+ "compute_energy": false,
94
+ "compute_linear_spec": true,
95
+ "precompute_num_workers": 0,
96
+ "start_by_longest": false,
97
+ "shuffle": false,
98
+ "drop_last": false,
99
+ "datasets": [
100
+ {
101
+ "formatter": "ljspeech",
102
+ "dataset_name": "",
103
+ "path": "/home/zombie/TTS/recipes/ljspeech/vits_tts/attenborough/",
104
+ "meta_file_train": "metadata.csv",
105
+ "ignored_speakers": null,
106
+ "language": "",
107
+ "phonemizer": "",
108
+ "meta_file_val": "",
109
+ "meta_file_attn_mask": ""
110
+ }
111
+ ],
112
+ "test_sentences": [
113
+ [
114
+ "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent."
115
+ ],
116
+ [
117
+ "Be a voice, not an echo."
118
+ ],
119
+ [
120
+ "I'm sorry Dave. I'm afraid I can't do that."
121
+ ],
122
+ [
123
+ "This cake is great. It's so delicious and moist."
124
+ ],
125
+ [
126
+ "Prior to November 22, 1963."
127
+ ]
128
+ ],
129
+ "eval_split_max_size": null,
130
+ "eval_split_size": 0.01,
131
+ "use_speaker_weighted_sampler": false,
132
+ "speaker_weighted_sampler_alpha": 1.0,
133
+ "use_language_weighted_sampler": false,
134
+ "language_weighted_sampler_alpha": 1.0,
135
+ "use_length_weighted_sampler": false,
136
+ "length_weighted_sampler_alpha": 1.0,
137
+ "model_args": {
138
+ "num_chars": 131,
139
+ "out_channels": 513,
140
+ "spec_segment_size": 32,
141
+ "hidden_channels": 192,
142
+ "hidden_channels_ffn_text_encoder": 768,
143
+ "num_heads_text_encoder": 2,
144
+ "num_layers_text_encoder": 6,
145
+ "kernel_size_text_encoder": 3,
146
+ "dropout_p_text_encoder": 0.1,
147
+ "dropout_p_duration_predictor": 0.5,
148
+ "kernel_size_posterior_encoder": 5,
149
+ "dilation_rate_posterior_encoder": 1,
150
+ "num_layers_posterior_encoder": 16,
151
+ "kernel_size_flow": 5,
152
+ "dilation_rate_flow": 1,
153
+ "num_layers_flow": 4,
154
+ "resblock_type_decoder": "1",
155
+ "resblock_kernel_sizes_decoder": [
156
+ 3,
157
+ 7,
158
+ 11
159
+ ],
160
+ "resblock_dilation_sizes_decoder": [
161
+ [
162
+ 1,
163
+ 3,
164
+ 5
165
+ ],
166
+ [
167
+ 1,
168
+ 3,
169
+ 5
170
+ ],
171
+ [
172
+ 1,
173
+ 3,
174
+ 5
175
+ ]
176
+ ],
177
+ "upsample_rates_decoder": [
178
+ 8,
179
+ 8,
180
+ 2,
181
+ 2
182
+ ],
183
+ "upsample_initial_channel_decoder": 512,
184
+ "upsample_kernel_sizes_decoder": [
185
+ 16,
186
+ 16,
187
+ 4,
188
+ 4
189
+ ],
190
+ "periods_multi_period_discriminator": [
191
+ 2,
192
+ 3,
193
+ 5,
194
+ 7,
195
+ 11
196
+ ],
197
+ "use_sdp": true,
198
+ "noise_scale": 1.0,
199
+ "inference_noise_scale": 0.667,
200
+ "length_scale": 1,
201
+ "noise_scale_dp": 1.0,
202
+ "inference_noise_scale_dp": 1.0,
203
+ "max_inference_len": null,
204
+ "init_discriminator": true,
205
+ "use_spectral_norm_disriminator": false,
206
+ "use_speaker_embedding": false,
207
+ "num_speakers": 0,
208
+ "speakers_file": null,
209
+ "d_vector_file": null,
210
+ "speaker_embedding_channels": 256,
211
+ "use_d_vector_file": false,
212
+ "d_vector_dim": 0,
213
+ "detach_dp_input": true,
214
+ "use_language_embedding": false,
215
+ "embedded_language_dim": 4,
216
+ "num_languages": 0,
217
+ "language_ids_file": null,
218
+ "use_speaker_encoder_as_loss": false,
219
+ "speaker_encoder_config_path": "",
220
+ "speaker_encoder_model_path": "",
221
+ "condition_dp_on_speaker": true,
222
+ "freeze_encoder": false,
223
+ "freeze_DP": false,
224
+ "freeze_PE": false,
225
+ "freeze_flow_decoder": false,
226
+ "freeze_waveform_decoder": false,
227
+ "encoder_sample_rate": null,
228
+ "interpolate_z": true,
229
+ "reinit_DP": false,
230
+ "reinit_text_encoder": false
231
+ },
232
+ "lr_gen": 0.0002,
233
+ "lr_disc": 0.0002,
234
+ "lr_scheduler_gen": "ExponentialLR",
235
+ "lr_scheduler_gen_params": {
236
+ "gamma": 0.999875,
237
+ "last_epoch": -1
238
+ },
239
+ "lr_scheduler_disc": "ExponentialLR",
240
+ "lr_scheduler_disc_params": {
241
+ "gamma": 0.999875,
242
+ "last_epoch": -1
243
+ },
244
+ "kl_loss_alpha": 1.0,
245
+ "disc_loss_alpha": 1.0,
246
+ "gen_loss_alpha": 1.0,
247
+ "feat_loss_alpha": 1.0,
248
+ "mel_loss_alpha": 45.0,
249
+ "dur_loss_alpha": 1.0,
250
+ "speaker_encoder_loss_alpha": 1.0,
251
+ "return_wav": true,
252
+ "use_weighted_sampler": false,
253
+ "weighted_sampler_attrs": {},
254
+ "weighted_sampler_multipliers": {},
255
+ "r": 1,
256
+ "num_speakers": 0,
257
+ "use_speaker_embedding": false,
258
+ "speakers_file": null,
259
+ "speaker_embedding_channels": 256,
260
+ "language_ids_file": null,
261
+ "use_language_embedding": false,
262
+ "use_d_vector_file": false,
263
+ "d_vector_file": null,
264
+ "d_vector_dim": 0,
265
+ "github_branch": "* dev"
266
+ }
david_attenborough_checkpoint_2020000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2655fc654d93ccdc89a8f3a9a14374a4853bfd3dd81efcb9444e1fcb6c268688
3
+ size 997870789
james_earl_jones_checkpoint_1600000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6acf6bb832a5a7fcd947575735cd0593092eb400a277d0778c459993a5d11dd6
3
+ size 997870597
neil_degrasse_tyson_checkpoint_1910000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4196795a6e443c6d1097b509a02d597a51c2e4e2d73f3fd27b9b2a2619500c
3
+ size 997870597
tim_dillon_checkpoint_1970000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b390353b1cf93ca07821c546d234cf4ebe882afaa32b1f70babd188180911235
3
+ size 997870597
vincent_price_checkpoint_2080000.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed23244a00e5c5f020866278e597684b9497217dbc798f306628d41765d0811c
3
+ size 997870725