marianbasti
commited on
Commit
•
77dc1e6
1
Parent(s):
0caff00
Upload 2 files
Browse files- config.json +204 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,204 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"output_path": "train",
|
3 |
+
"logger_uri": null,
|
4 |
+
"run_name": "GPT_XTTS_v2.0_argentine",
|
5 |
+
"project_name": "XTTS_argentine",
|
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": 1000,
|
14 |
+
"save_step": 10000,
|
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": 1000,
|
29 |
+
"batch_size": 8,
|
30 |
+
"eval_batch_size": 8,
|
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 |
+
{
|
106 |
+
"text": "Loco, no puede ser! Cuanta memoria del orto necesito para entrenar este modelo?",
|
107 |
+
"speaker_wav": [
|
108 |
+
"/home/HPC-LLM/TTS/MyTTSDataset/wavs/female_0.wav"
|
109 |
+
],
|
110 |
+
"language": "es"
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"text": "Es una locura. Se pueden ir todos a la mierda.",
|
114 |
+
"speaker_wav": [
|
115 |
+
"/home/HPC-LLM/TTS/MyTTSDataset/wavs/female_0.wav"
|
116 |
+
],
|
117 |
+
"language": "es"
|
118 |
+
}
|
119 |
+
],
|
120 |
+
"eval_split_max_size": 256,
|
121 |
+
"eval_split_size": 0.01,
|
122 |
+
"use_speaker_weighted_sampler": false,
|
123 |
+
"speaker_weighted_sampler_alpha": 1.0,
|
124 |
+
"use_language_weighted_sampler": false,
|
125 |
+
"language_weighted_sampler_alpha": 1.0,
|
126 |
+
"use_length_weighted_sampler": false,
|
127 |
+
"length_weighted_sampler_alpha": 1.0,
|
128 |
+
"model_args": {
|
129 |
+
"gpt_batch_size": 1,
|
130 |
+
"enable_redaction": false,
|
131 |
+
"kv_cache": true,
|
132 |
+
"gpt_checkpoint": "",
|
133 |
+
"clvp_checkpoint": null,
|
134 |
+
"decoder_checkpoint": null,
|
135 |
+
"num_chars": 255,
|
136 |
+
"tokenizer_file": "train/XTTS_v2.0_original_model_files/vocab.json",
|
137 |
+
"gpt_max_audio_tokens": 605,
|
138 |
+
"gpt_max_text_tokens": 402,
|
139 |
+
"gpt_max_prompt_tokens": 70,
|
140 |
+
"gpt_layers": 30,
|
141 |
+
"gpt_n_model_channels": 1024,
|
142 |
+
"gpt_n_heads": 16,
|
143 |
+
"gpt_number_text_tokens": 6681,
|
144 |
+
"gpt_start_text_token": 261,
|
145 |
+
"gpt_stop_text_token": 0,
|
146 |
+
"gpt_num_audio_tokens": 1026,
|
147 |
+
"gpt_start_audio_token": 1024,
|
148 |
+
"gpt_stop_audio_token": 1025,
|
149 |
+
"gpt_code_stride_len": 1024,
|
150 |
+
"gpt_use_masking_gt_prompt_approach": true,
|
151 |
+
"gpt_use_perceiver_resampler": true,
|
152 |
+
"input_sample_rate": 22050,
|
153 |
+
"output_sample_rate": 24000,
|
154 |
+
"output_hop_length": 256,
|
155 |
+
"decoder_input_dim": 1024,
|
156 |
+
"d_vector_dim": 512,
|
157 |
+
"cond_d_vector_in_each_upsampling_layer": true,
|
158 |
+
"duration_const": 102400,
|
159 |
+
"min_conditioning_length": 66150,
|
160 |
+
"max_conditioning_length": 132300,
|
161 |
+
"gpt_loss_text_ce_weight": 0.01,
|
162 |
+
"gpt_loss_mel_ce_weight": 1.0,
|
163 |
+
"debug_loading_failures": false,
|
164 |
+
"max_wav_length": 255995,
|
165 |
+
"max_text_length": 200,
|
166 |
+
"mel_norm_file": "train/XTTS_v2.0_original_model_files/mel_stats.pth",
|
167 |
+
"dvae_checkpoint": "train/XTTS_v2.0_original_model_files/dvae.pth",
|
168 |
+
"xtts_checkpoint": "train/XTTS_v2.0_original_model_files/model.pth",
|
169 |
+
"vocoder": ""
|
170 |
+
},
|
171 |
+
"model_dir": null,
|
172 |
+
"languages": [
|
173 |
+
"en",
|
174 |
+
"es",
|
175 |
+
"fr",
|
176 |
+
"de",
|
177 |
+
"it",
|
178 |
+
"pt",
|
179 |
+
"pl",
|
180 |
+
"tr",
|
181 |
+
"ru",
|
182 |
+
"nl",
|
183 |
+
"cs",
|
184 |
+
"ar",
|
185 |
+
"zh-cn",
|
186 |
+
"hu",
|
187 |
+
"ko",
|
188 |
+
"ja",
|
189 |
+
"hi"
|
190 |
+
],
|
191 |
+
"temperature": 0.85,
|
192 |
+
"length_penalty": 1.0,
|
193 |
+
"repetition_penalty": 2.0,
|
194 |
+
"top_k": 50,
|
195 |
+
"top_p": 0.85,
|
196 |
+
"num_gpt_outputs": 1,
|
197 |
+
"gpt_cond_len": 12,
|
198 |
+
"gpt_cond_chunk_len": 4,
|
199 |
+
"max_ref_len": 10,
|
200 |
+
"sound_norm_refs": false,
|
201 |
+
"optimizer_wd_only_on_weights": true,
|
202 |
+
"weighted_loss_attrs": null,
|
203 |
+
"weighted_loss_multipliers": null
|
204 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|