Ftfyhh commited on
Commit
49bc1d1
1 Parent(s): 1df83f6

Upload 4 files

Browse files
model_banana/v2.0.2/config.json ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "output_path": "/tmp/xtts_ft/run\\training",
3
+ "logger_uri": null,
4
+ "run_name": "GPT_XTTS_FT",
5
+ "project_name": "XTTS_trainer",
6
+ "run_description": "\n GPT XTTS training\n ",
7
+ "print_step": 50,
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": 100,
14
+ "save_step": 1000,
15
+ "save_n_checkpoints": 1,
16
+ "save_checkpoints": true,
17
+ "save_all_best": false,
18
+ "save_best_after": 0,
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": 25,
29
+ "batch_size": 4,
30
+ "eval_batch_size": 4,
31
+ "grad_clip": 0.0,
32
+ "scheduler_after_epoch": true,
33
+ "lr": 5e-06,
34
+ "optimizer": "AdamW",
35
+ "optimizer_params": {
36
+ "betas": [
37
+ 0.9,
38
+ 0.96
39
+ ],
40
+ "eps": 1e-08,
41
+ "weight_decay": 0.01
42
+ },
43
+ "lr_scheduler": "MultiStepLR",
44
+ "lr_scheduler_params": {
45
+ "milestones": [
46
+ 900000,
47
+ 2700000,
48
+ 5400000
49
+ ],
50
+ "gamma": 0.5,
51
+ "last_epoch": -1
52
+ },
53
+ "use_grad_scaler": false,
54
+ "allow_tf32": false,
55
+ "cudnn_enable": true,
56
+ "cudnn_deterministic": false,
57
+ "cudnn_benchmark": false,
58
+ "training_seed": 1,
59
+ "model": "xtts",
60
+ "num_loader_workers": 8,
61
+ "num_eval_loader_workers": 0,
62
+ "use_noise_augment": false,
63
+ "audio": {
64
+ "sample_rate": 22050,
65
+ "output_sample_rate": 24000,
66
+ "dvae_sample_rate": 22050
67
+ },
68
+ "use_phonemes": false,
69
+ "phonemizer": null,
70
+ "phoneme_language": null,
71
+ "compute_input_seq_cache": false,
72
+ "text_cleaner": null,
73
+ "enable_eos_bos_chars": false,
74
+ "test_sentences_file": "",
75
+ "phoneme_cache_path": null,
76
+ "characters": null,
77
+ "add_blank": false,
78
+ "batch_group_size": 48,
79
+ "loss_masking": null,
80
+ "min_audio_len": 1,
81
+ "max_audio_len": Infinity,
82
+ "min_text_len": 1,
83
+ "max_text_len": Infinity,
84
+ "compute_f0": false,
85
+ "compute_energy": false,
86
+ "compute_linear_spec": false,
87
+ "precompute_num_workers": 0,
88
+ "start_by_longest": false,
89
+ "shuffle": false,
90
+ "drop_last": false,
91
+ "datasets": [
92
+ {
93
+ "formatter": "",
94
+ "dataset_name": "",
95
+ "path": "",
96
+ "meta_file_train": "",
97
+ "ignored_speakers": null,
98
+ "language": "",
99
+ "phonemizer": "",
100
+ "meta_file_val": "",
101
+ "meta_file_attn_mask": ""
102
+ }
103
+ ],
104
+ "test_sentences": [],
105
+ "eval_split_max_size": 256,
106
+ "eval_split_size": 0.01,
107
+ "use_speaker_weighted_sampler": false,
108
+ "speaker_weighted_sampler_alpha": 1.0,
109
+ "use_language_weighted_sampler": false,
110
+ "language_weighted_sampler_alpha": 1.0,
111
+ "use_length_weighted_sampler": false,
112
+ "length_weighted_sampler_alpha": 1.0,
113
+ "model_args": {
114
+ "gpt_batch_size": 1,
115
+ "enable_redaction": false,
116
+ "kv_cache": true,
117
+ "gpt_checkpoint": "",
118
+ "clvp_checkpoint": null,
119
+ "decoder_checkpoint": null,
120
+ "num_chars": 255,
121
+ "tokenizer_file": "/tmp/xtts_ft/run\\training\\XTTS_v2.0_original_model_files/vocab.json",
122
+ "gpt_max_audio_tokens": 605,
123
+ "gpt_max_text_tokens": 402,
124
+ "gpt_max_prompt_tokens": 70,
125
+ "gpt_layers": 30,
126
+ "gpt_n_model_channels": 1024,
127
+ "gpt_n_heads": 16,
128
+ "gpt_number_text_tokens": 6681,
129
+ "gpt_start_text_token": 261,
130
+ "gpt_stop_text_token": 0,
131
+ "gpt_num_audio_tokens": 1026,
132
+ "gpt_start_audio_token": 1024,
133
+ "gpt_stop_audio_token": 1025,
134
+ "gpt_code_stride_len": 1024,
135
+ "gpt_use_masking_gt_prompt_approach": true,
136
+ "gpt_use_perceiver_resampler": true,
137
+ "input_sample_rate": 22050,
138
+ "output_sample_rate": 24000,
139
+ "output_hop_length": 256,
140
+ "decoder_input_dim": 1024,
141
+ "d_vector_dim": 512,
142
+ "cond_d_vector_in_each_upsampling_layer": true,
143
+ "duration_const": 102400,
144
+ "min_conditioning_length": 66150,
145
+ "max_conditioning_length": 132300,
146
+ "gpt_loss_text_ce_weight": 0.01,
147
+ "gpt_loss_mel_ce_weight": 1.0,
148
+ "debug_loading_failures": false,
149
+ "max_wav_length": 242550,
150
+ "max_text_length": 200,
151
+ "mel_norm_file": "/tmp/xtts_ft/run\\training\\XTTS_v2.0_original_model_files/mel_stats.pth",
152
+ "dvae_checkpoint": "/tmp/xtts_ft/run\\training\\XTTS_v2.0_original_model_files/dvae.pth",
153
+ "xtts_checkpoint": "/tmp/xtts_ft/run\\training\\XTTS_v2.0_original_model_files/model.pth",
154
+ "vocoder": ""
155
+ },
156
+ "model_dir": null,
157
+ "languages": [
158
+ "en",
159
+ "es",
160
+ "fr",
161
+ "de",
162
+ "it",
163
+ "pt",
164
+ "pl",
165
+ "tr",
166
+ "ru",
167
+ "nl",
168
+ "cs",
169
+ "ar",
170
+ "zh-cn",
171
+ "hu",
172
+ "ko",
173
+ "ja",
174
+ "hi"
175
+ ],
176
+ "temperature": 0.85,
177
+ "length_penalty": 1.0,
178
+ "repetition_penalty": 2.0,
179
+ "top_k": 50,
180
+ "top_p": 0.85,
181
+ "num_gpt_outputs": 1,
182
+ "gpt_cond_len": 12,
183
+ "gpt_cond_chunk_len": 4,
184
+ "max_ref_len": 10,
185
+ "sound_norm_refs": false,
186
+ "optimizer_wd_only_on_weights": true,
187
+ "weighted_loss_attrs": {},
188
+ "weighted_loss_multipliers": {},
189
+ "github_branch": "inside_docker"
190
+ }
model_banana/v2.0.2/model.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae9bb3df55264233bd57b133f4681476a3f64f2c408c669e5afc2b87639053e
3
+ size 5607926933
model_banana/v2.0.2/speakers_xtts.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f6137c19a4eab0cbbe4c99b5babacf68b1746e50da90807708c10e645b943b
3
+ size 7754818
model_banana/v2.0.2/vocab.json ADDED
The diff for this file is too large to render. See raw diff