File size: 7,124 Bytes
f844c16 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 |
{
"output_path": "/home/odin/slava/xtts2_training/TTS/recipes/ljspeech/xtts_v2/run/training",
"logger_uri": null,
"run_name": "GPT_XTTS_v2.0_LJSpeech_FT",
"project_name": "XTTS_trainer",
"run_description": "\n GPT XTTS training\n ",
"print_step": 50,
"plot_step": 100,
"model_param_stats": false,
"wandb_entity": null,
"dashboard_logger": "tensorboard",
"save_on_interrupt": true,
"log_model_step": 1000,
"save_step": 10000,
"save_n_checkpoints": 1,
"save_checkpoints": true,
"save_all_best": false,
"save_best_after": 0,
"target_loss": null,
"print_eval": false,
"test_delay_epochs": 0,
"run_eval": true,
"run_eval_steps": null,
"distributed_backend": "nccl",
"distributed_url": "tcp://localhost:54321",
"mixed_precision": false,
"precision": "fp16",
"epochs": 1000,
"batch_size": 3,
"eval_batch_size": 3,
"grad_clip": 0.0,
"scheduler_after_epoch": true,
"lr": 5e-06,
"optimizer": "AdamW",
"optimizer_params": {
"betas": [
0.9,
0.96
],
"eps": 1e-08,
"weight_decay": 0.01
},
"lr_scheduler": "MultiStepLR",
"lr_scheduler_params": {
"milestones": [
900000,
2700000,
5400000
],
"gamma": 0.5,
"last_epoch": -1
},
"use_grad_scaler": false,
"allow_tf32": false,
"cudnn_enable": true,
"cudnn_deterministic": false,
"cudnn_benchmark": false,
"training_seed": 1,
"model": "xtts",
"num_loader_workers": 8,
"num_eval_loader_workers": 0,
"use_noise_augment": false,
"audio": {
"sample_rate": 22050,
"output_sample_rate": 24000,
"dvae_sample_rate": 22050
},
"use_phonemes": false,
"phonemizer": null,
"phoneme_language": null,
"compute_input_seq_cache": false,
"text_cleaner": null,
"enable_eos_bos_chars": false,
"test_sentences_file": "",
"phoneme_cache_path": null,
"characters": null,
"add_blank": false,
"batch_group_size": 48,
"loss_masking": null,
"min_audio_len": 1,
"max_audio_len": Infinity,
"min_text_len": 1,
"max_text_len": Infinity,
"compute_f0": false,
"compute_energy": false,
"compute_linear_spec": false,
"precompute_num_workers": 0,
"start_by_longest": false,
"shuffle": false,
"drop_last": false,
"datasets": [
{
"formatter": "",
"dataset_name": "",
"path": "",
"meta_file_train": "",
"ignored_speakers": null,
"language": "",
"phonemizer": "",
"meta_file_val": "",
"meta_file_attn_mask": ""
}
],
"test_sentences": [
{
"text": "\u0412 \u0434\u0430\u043b+\u0438 \u0432\u0438\u0434\u043d+\u0435\u043b\u0441\u044f \u0441\u0442+\u0430\u0440\u044b\u0439 \u0437+\u0430\u043c\u043e\u043a, \u043a\u043e\u0442+\u043e\u0440\u044b\u0439 \u043c\u044b \u0440\u0435\u0448+\u0438\u043b\u0438 \u043e\u0441\u043c\u043e\u0442\u0440+\u0435\u0442\u044c, \u043d+\u043e +\u0438\u0437-\u0437+\u0430 \u043d\u0435\u043f\u043e\u0433+\u043e\u0434\u044b \u043d+\u0430\u0448 \u0437+\u0430\u043c\u043e\u043a \u043d+\u0430 \u0440\u0435\u043a+\u0435 \u0431+\u044b\u043b \u0441\u043d\u0435\u0441+\u0451\u043d.",
"speaker_wav": [
"LJSpeech-1.1/wavs/022199_RUSLAN.wav"
],
"language": "ru"
},
{
"text": "\u041f\u0440\u0438\u0433\u043e\u0432+\u043e\u0440\u0435\u043d\u043d\u044b\u0439 \u0441 \u043c+\u0443\u043a\u043e\u0439 \u043f\u0440\u0438\u043d\u0438\u043c+\u0430\u043b \u0441\u0432\u043e+\u044e \u0441\u0443\u0434\u044c\u0431+\u0443, \u043f\u043e\u043a+\u0430 \u0435\u0433+\u043e \u0436\u0435\u043d+\u0430 \u0433\u043e\u0442+\u043e\u0432\u0438\u043b\u0430 \u043f\u0438\u0440+\u043e\u0433 +\u0438\u0437 \u0441\u0432+\u0435\u0436\u0435\u0439 \u043c\u0443\u043a+\u0438.",
"speaker_wav": [
"LJSpeech-1.1/wavs/022199_RUSLAN.wav"
],
"language": "ru"
}
],
"eval_split_max_size": 256,
"eval_split_size": 0.01,
"use_speaker_weighted_sampler": false,
"speaker_weighted_sampler_alpha": 1.0,
"use_language_weighted_sampler": false,
"language_weighted_sampler_alpha": 1.0,
"use_length_weighted_sampler": false,
"length_weighted_sampler_alpha": 1.0,
"model_args": {
"gpt_batch_size": 1,
"enable_redaction": false,
"kv_cache": true,
"gpt_checkpoint": "",
"clvp_checkpoint": null,
"decoder_checkpoint": null,
"num_chars": 255,
"tokenizer_file": "/home/odin/slava/xtts2_training/TTS/recipes/ljspeech/xtts_v2/run/training/XTTS_v2.0_original_model_files/vocab.json",
"gpt_max_audio_tokens": 605,
"gpt_max_text_tokens": 402,
"gpt_max_prompt_tokens": 70,
"gpt_layers": 30,
"gpt_n_model_channels": 1024,
"gpt_n_heads": 16,
"gpt_number_text_tokens": 6682,
"gpt_start_text_token": 261,
"gpt_stop_text_token": 0,
"gpt_num_audio_tokens": 1026,
"gpt_start_audio_token": 1024,
"gpt_stop_audio_token": 1025,
"gpt_code_stride_len": 1024,
"gpt_use_masking_gt_prompt_approach": true,
"gpt_use_perceiver_resampler": true,
"input_sample_rate": 22050,
"output_sample_rate": 24000,
"output_hop_length": 256,
"decoder_input_dim": 1024,
"d_vector_dim": 512,
"cond_d_vector_in_each_upsampling_layer": true,
"duration_const": 102400,
"min_conditioning_length": 66150,
"max_conditioning_length": 132300,
"gpt_loss_text_ce_weight": 0.01,
"gpt_loss_mel_ce_weight": 1.0,
"debug_loading_failures": false,
"max_wav_length": 255995,
"max_text_length": 200,
"mel_norm_file": "/home/odin/slava/xtts2_training/TTS/recipes/ljspeech/xtts_v2/run/training/XTTS_v2.0_original_model_files/mel_stats.pth",
"dvae_checkpoint": "/home/odin/slava/xtts2_training/TTS/recipes/ljspeech/xtts_v2/run/training/XTTS_v2.0_original_model_files/dvae.pth",
"xtts_checkpoint": "/home/odin/slava/xtts2_training/TTS/recipes/ljspeech/xtts_v2/run/training/XTTS_v2.0_original_model_files/model.pth",
"vocoder": ""
},
"model_dir": null,
"languages": [
"en",
"es",
"fr",
"de",
"it",
"pt",
"pl",
"tr",
"ru",
"nl",
"cs",
"ar",
"zh-cn",
"hu",
"ko",
"ja",
"hi"
],
"temperature": 0.85,
"length_penalty": 1.0,
"repetition_penalty": 2.0,
"top_k": 50,
"top_p": 0.85,
"num_gpt_outputs": 1,
"gpt_cond_len": 12,
"gpt_cond_chunk_len": 4,
"max_ref_len": 10,
"sound_norm_refs": false,
"optimizer_wd_only_on_weights": true,
"weighted_loss_attrs": {},
"weighted_loss_multipliers": {},
"github_branch": "* dev"
} |