|
{ |
|
"output_path": "H:\\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": 10000, |
|
"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": "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.", |
|
"speaker_wav": [ |
|
"H:/ai-voice-cloning/training/adam/wavs/adam_00001.wav" |
|
], |
|
"language": "en" |
|
}, |
|
{ |
|
"text": "The sun hadn't quite settled into its stride over the sky, but that didn't prevent it from having already toasted the earth and grass until they released a rich, deep smell of hay.", |
|
"speaker_wav": [ |
|
"H:/ai-voice-cloning/training/adam/wavs/adam_00001.wav" |
|
], |
|
"language": "en" |
|
} |
|
], |
|
"eval_split_max_size": 256, |
|
"eval_split_size": 0.2, |
|
"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": "H:\\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": 6153, |
|
"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": "H:\\TTS\\recipes\\ljspeech\\xtts_v2\\run\\training\\XTTS_v2.0_original_model_files/mel_stats.pth", |
|
"dvae_checkpoint": "H:\\TTS\\recipes\\ljspeech\\xtts_v2\\run\\training\\XTTS_v2.0_original_model_files/dvae.pth", |
|
"xtts_checkpoint": "H:\\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" |
|
], |
|
"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": 3, |
|
"max_ref_len": 10, |
|
"sound_norm_refs": false, |
|
"optimizer_wd_only_on_weights": true, |
|
"weighted_loss_attrs": {}, |
|
"weighted_loss_multipliers": {}, |
|
"github_branch": "* dev" |
|
} |