Text-to-Speech
coqui
erogol commited on
Commit
2ee4929
1 Parent(s): b317f99

Add metafiles files

Browse files
Files changed (3) hide show
  1. config.json +175 -0
  2. hash.md5 +1 -0
  3. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,175 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "save_on_interrupt": true,
13
+ "log_model_step": null,
14
+ "save_step": 10000,
15
+ "save_n_checkpoints": 5,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 10000,
19
+ "target_loss": null,
20
+ "print_eval": false,
21
+ "test_delay_epochs": 0,
22
+ "run_eval": true,
23
+ "run_eval_steps": null,
24
+ "distributed_backend": "nccl",
25
+ "distributed_url": "tcp://localhost:54321",
26
+ "mixed_precision": false,
27
+ "precision": "fp16",
28
+ "epochs": 1000,
29
+ "batch_size": 32,
30
+ "eval_batch_size": 16,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 0.001,
34
+ "optimizer": "radam",
35
+ "optimizer_params": null,
36
+ "lr_scheduler": null,
37
+ "lr_scheduler_params": {},
38
+ "use_grad_scaler": false,
39
+ "allow_tf32": false,
40
+ "cudnn_enable": true,
41
+ "cudnn_deterministic": false,
42
+ "cudnn_benchmark": false,
43
+ "training_seed": 54321,
44
+ "model": "xtts",
45
+ "num_loader_workers": 0,
46
+ "num_eval_loader_workers": 0,
47
+ "use_noise_augment": false,
48
+ "audio": {
49
+ "sample_rate": 22050,
50
+ "diffusion_sample_rate": 24000,
51
+ "output_sample_rate": 24000
52
+ },
53
+ "use_phonemes": false,
54
+ "phonemizer": null,
55
+ "phoneme_language": null,
56
+ "compute_input_seq_cache": false,
57
+ "text_cleaner": null,
58
+ "enable_eos_bos_chars": false,
59
+ "test_sentences_file": "",
60
+ "phoneme_cache_path": null,
61
+ "characters": null,
62
+ "add_blank": false,
63
+ "batch_group_size": 0,
64
+ "loss_masking": null,
65
+ "min_audio_len": 1,
66
+ "max_audio_len": Infinity,
67
+ "min_text_len": 1,
68
+ "max_text_len": Infinity,
69
+ "compute_f0": false,
70
+ "compute_energy": false,
71
+ "compute_linear_spec": false,
72
+ "precompute_num_workers": 0,
73
+ "start_by_longest": false,
74
+ "shuffle": false,
75
+ "drop_last": false,
76
+ "datasets": [
77
+ {
78
+ "formatter": "",
79
+ "dataset_name": "",
80
+ "path": "",
81
+ "meta_file_train": "",
82
+ "ignored_speakers": null,
83
+ "language": "",
84
+ "phonemizer": "",
85
+ "meta_file_val": "",
86
+ "meta_file_attn_mask": ""
87
+ }
88
+ ],
89
+ "test_sentences": [],
90
+ "eval_split_max_size": null,
91
+ "eval_split_size": 0.01,
92
+ "use_speaker_weighted_sampler": false,
93
+ "speaker_weighted_sampler_alpha": 1.0,
94
+ "use_language_weighted_sampler": false,
95
+ "language_weighted_sampler_alpha": 1.0,
96
+ "use_length_weighted_sampler": false,
97
+ "length_weighted_sampler_alpha": 1.0,
98
+ "model_args": {
99
+ "gpt_batch_size": 1,
100
+ "enable_redaction": false,
101
+ "kv_cache": true,
102
+ "gpt_checkpoint": null,
103
+ "clvp_checkpoint": null,
104
+ "decoder_checkpoint": null,
105
+ "num_chars": 255,
106
+ "use_hifigan": true,
107
+ "use_ne_hifigan": false,
108
+ "tokenizer_file": "",
109
+ "gpt_max_audio_tokens": 605,
110
+ "gpt_max_text_tokens": 402,
111
+ "gpt_max_prompt_tokens": 70,
112
+ "gpt_layers": 30,
113
+ "gpt_n_model_channels": 1024,
114
+ "gpt_n_heads": 16,
115
+ "gpt_number_text_tokens": 6153,
116
+ "gpt_start_text_token": null,
117
+ "gpt_stop_text_token": null,
118
+ "gpt_num_audio_tokens": 1026,
119
+ "gpt_start_audio_token": 1024,
120
+ "gpt_stop_audio_token": 1025,
121
+ "gpt_code_stride_len": 1024,
122
+ "gpt_use_masking_gt_prompt_approach": true,
123
+ "gpt_use_perceiver_resampler": true,
124
+ "diff_model_channels": 1024,
125
+ "diff_num_layers": 10,
126
+ "diff_in_channels": 100,
127
+ "diff_out_channels": 200,
128
+ "diff_in_latent_channels": 1024,
129
+ "diff_in_tokens": 8193,
130
+ "diff_dropout": 0,
131
+ "diff_use_fp16": false,
132
+ "diff_num_heads": 16,
133
+ "diff_layer_drop": 0,
134
+ "diff_unconditioned_percentage": 0,
135
+ "input_sample_rate": 22050,
136
+ "output_sample_rate": 24000,
137
+ "output_hop_length": 256,
138
+ "decoder_input_dim": 1024,
139
+ "d_vector_dim": 512,
140
+ "cond_d_vector_in_each_upsampling_layer": true,
141
+ "duration_const": 102400
142
+ },
143
+ "model_dir": null,
144
+ "languages": [
145
+ "en",
146
+ "es",
147
+ "fr",
148
+ "de",
149
+ "it",
150
+ "pt",
151
+ "pl",
152
+ "tr",
153
+ "ru",
154
+ "nl",
155
+ "cs",
156
+ "ar",
157
+ "zh-cn",
158
+ "hu",
159
+ "ko",
160
+ "ja"
161
+ ],
162
+ "temperature": 0.7,
163
+ "length_penalty": 1.0,
164
+ "repetition_penalty": 2.0,
165
+ "top_k": 100,
166
+ "top_p": 0.65,
167
+ "cond_free_k": 2.0,
168
+ "diffusion_temperature": 1.0,
169
+ "num_gpt_outputs": 1,
170
+ "decoder_iterations": 30,
171
+ "decoder_sampler": "ddim",
172
+ "gpt_cond_len": 30,
173
+ "max_ref_len": 30,
174
+ "sound_norm_refs": false
175
+ }
hash.md5 ADDED
@@ -0,0 +1 @@
 
 
1
+ ae9e4b39e095fd5728fe7f7931eccoqui
vocab.json ADDED
The diff for this file is too large to render. See raw diff