|
{ |
|
"output_path": null, |
|
"logger_uri": null, |
|
"run_name": "", |
|
"project_name": null, |
|
"run_description": "", |
|
"print_step": 25, |
|
"plot_step": 100, |
|
"model_param_stats": false, |
|
"wandb_entity": null, |
|
"dashboard_logger": "tensorboard", |
|
"save_on_interrupt": true, |
|
"log_model_step": null, |
|
"save_step": 10000, |
|
"save_n_checkpoints": 5, |
|
"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": 10000, |
|
"batch_size": null, |
|
"eval_batch_size": null, |
|
"grad_clip": [ |
|
5.0, |
|
5.0 |
|
], |
|
"scheduler_after_epoch": true, |
|
"lr": 0.001, |
|
"optimizer": "AdamW", |
|
"optimizer_params": { |
|
"betas": [ |
|
0.8, |
|
0.99 |
|
], |
|
"eps": 1e-09, |
|
"weight_decay": 0.01 |
|
}, |
|
"lr_scheduler": "", |
|
"lr_scheduler_params": {}, |
|
"use_grad_scaler": false, |
|
"allow_tf32": false, |
|
"cudnn_enable": true, |
|
"cudnn_deterministic": false, |
|
"cudnn_benchmark": true, |
|
"training_seed": 54321, |
|
"model": "vits", |
|
"num_loader_workers": null, |
|
"num_eval_loader_workers": 0, |
|
"use_noise_augment": false, |
|
"audio": { |
|
"fft_size": 1024, |
|
"sample_rate": 22050, |
|
"win_length": 1024, |
|
"hop_length": 256, |
|
"num_mels": 80, |
|
"mel_fmin": 0, |
|
"mel_fmax": null |
|
}, |
|
"use_phonemes": true, |
|
"phonemizer": "espeak", |
|
"phoneme_language": "en", |
|
"compute_input_seq_cache": false, |
|
"text_cleaner": "phoneme_cleaners", |
|
"enable_eos_bos_chars": false, |
|
"test_sentences_file": "", |
|
"phoneme_cache_path": null, |
|
"characters": { |
|
"characters_class": "TTS.tts.models.vits.VitsCharacters", |
|
"vocab_dict": null, |
|
"pad": "_", |
|
"eos": "", |
|
"bos": "", |
|
"blank": null, |
|
"characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz", |
|
"punctuations": ";:,.!?\u00a1\u00bf\u2014\u2026\"\u00ab\u00bb\u201c\u201d ", |
|
"phonemes": "\u0251\u0250\u0252\u00e6\u0253\u0299\u03b2\u0254\u0255\u00e7\u0257\u0256\u00f0\u02a4\u0259\u0258\u025a\u025b\u025c\u025d\u025e\u025f\u0284\u0261\u0260\u0262\u029b\u0266\u0267\u0127\u0265\u029c\u0268\u026a\u029d\u026d\u026c\u026b\u026e\u029f\u0271\u026f\u0270\u014b\u0273\u0272\u0274\u00f8\u0275\u0278\u03b8\u0153\u0276\u0298\u0279\u027a\u027e\u027b\u0280\u0281\u027d\u0282\u0283\u0288\u02a7\u0289\u028a\u028b\u2c71\u028c\u0263\u0264\u028d\u03c7\u028e\u028f\u0291\u0290\u0292\u0294\u02a1\u0295\u02a2\u01c0\u01c1\u01c2\u01c3\u02c8\u02cc\u02d0\u02d1\u02bc\u02b4\u02b0\u02b1\u02b2\u02b7\u02e0\u02e4\u02de\u2193\u2191\u2192\u2197\u2198'\u0329'\u1d7b", |
|
"is_unique": true, |
|
"is_sorted": true |
|
}, |
|
"add_blank": true, |
|
"batch_group_size": 0, |
|
"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": true, |
|
"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": [ |
|
[ |
|
"I", |
|
"t", |
|
" ", |
|
"t", |
|
"o", |
|
"o", |
|
"k", |
|
" ", |
|
"m", |
|
"e", |
|
" ", |
|
"q", |
|
"u", |
|
"i", |
|
"t", |
|
"e", |
|
" ", |
|
"a", |
|
" ", |
|
"l", |
|
"o", |
|
"n", |
|
"g", |
|
" ", |
|
"t", |
|
"i", |
|
"m", |
|
"e", |
|
" ", |
|
"t", |
|
"o", |
|
" ", |
|
"d", |
|
"e", |
|
"v", |
|
"e", |
|
"l", |
|
"o", |
|
"p", |
|
" ", |
|
"a", |
|
" ", |
|
"v", |
|
"o", |
|
"i", |
|
"c", |
|
"e", |
|
",", |
|
" ", |
|
"a", |
|
"n", |
|
"d", |
|
" ", |
|
"n", |
|
"o", |
|
"w", |
|
" ", |
|
"t", |
|
"h", |
|
"a", |
|
"t", |
|
" ", |
|
"I", |
|
" ", |
|
"h", |
|
"a", |
|
"v", |
|
"e", |
|
" ", |
|
"i", |
|
"t", |
|
" ", |
|
"I", |
|
"'", |
|
"m", |
|
" ", |
|
"n", |
|
"o", |
|
"t", |
|
" ", |
|
"g", |
|
"o", |
|
"i", |
|
"n", |
|
"g", |
|
" ", |
|
"t", |
|
"o", |
|
" ", |
|
"b", |
|
"e", |
|
" ", |
|
"s", |
|
"i", |
|
"l", |
|
"e", |
|
"n", |
|
"t", |
|
"." |
|
], |
|
[ |
|
"B", |
|
"e", |
|
" ", |
|
"a", |
|
" ", |
|
"v", |
|
"o", |
|
"i", |
|
"c", |
|
"e", |
|
",", |
|
" ", |
|
"n", |
|
"o", |
|
"t", |
|
" ", |
|
"a", |
|
"n", |
|
" ", |
|
"e", |
|
"c", |
|
"h", |
|
"o", |
|
"." |
|
], |
|
[ |
|
"I", |
|
"'", |
|
"m", |
|
" ", |
|
"s", |
|
"o", |
|
"r", |
|
"r", |
|
"y", |
|
" ", |
|
"D", |
|
"a", |
|
"v", |
|
"e", |
|
".", |
|
" ", |
|
"I", |
|
"'", |
|
"m", |
|
" ", |
|
"a", |
|
"f", |
|
"r", |
|
"a", |
|
"i", |
|
"d", |
|
" ", |
|
"I", |
|
" ", |
|
"c", |
|
"a", |
|
"n", |
|
"'", |
|
"t", |
|
" ", |
|
"d", |
|
"o", |
|
" ", |
|
"t", |
|
"h", |
|
"a", |
|
"t", |
|
"." |
|
], |
|
[ |
|
"T", |
|
"h", |
|
"i", |
|
"s", |
|
" ", |
|
"c", |
|
"a", |
|
"k", |
|
"e", |
|
" ", |
|
"i", |
|
"s", |
|
" ", |
|
"g", |
|
"r", |
|
"e", |
|
"a", |
|
"t", |
|
".", |
|
" ", |
|
"I", |
|
"t", |
|
"'", |
|
"s", |
|
" ", |
|
"s", |
|
"o", |
|
" ", |
|
"d", |
|
"e", |
|
"l", |
|
"i", |
|
"c", |
|
"i", |
|
"o", |
|
"u", |
|
"s", |
|
" ", |
|
"a", |
|
"n", |
|
"d", |
|
" ", |
|
"m", |
|
"o", |
|
"i", |
|
"s", |
|
"t", |
|
"." |
|
], |
|
[ |
|
"P", |
|
"r", |
|
"i", |
|
"o", |
|
"r", |
|
" ", |
|
"t", |
|
"o", |
|
" ", |
|
"N", |
|
"o", |
|
"v", |
|
"e", |
|
"m", |
|
"b", |
|
"e", |
|
"r", |
|
" ", |
|
"2", |
|
"2", |
|
",", |
|
" ", |
|
"1", |
|
"9", |
|
"6", |
|
"3", |
|
"." |
|
] |
|
], |
|
"eval_split_max_size": null, |
|
"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": { |
|
"num_chars": 179, |
|
"out_channels": 513, |
|
"spec_segment_size": 32, |
|
"hidden_channels": 192, |
|
"hidden_channels_ffn_text_encoder": 768, |
|
"num_heads_text_encoder": 2, |
|
"num_layers_text_encoder": 6, |
|
"kernel_size_text_encoder": 3, |
|
"dropout_p_text_encoder": 0.1, |
|
"dropout_p_duration_predictor": 0.5, |
|
"kernel_size_posterior_encoder": 5, |
|
"dilation_rate_posterior_encoder": 1, |
|
"num_layers_posterior_encoder": 16, |
|
"kernel_size_flow": 5, |
|
"dilation_rate_flow": 1, |
|
"num_layers_flow": 4, |
|
"resblock_type_decoder": "1", |
|
"resblock_kernel_sizes_decoder": [ |
|
3, |
|
7, |
|
11 |
|
], |
|
"resblock_dilation_sizes_decoder": [ |
|
[ |
|
1, |
|
3, |
|
5 |
|
], |
|
[ |
|
1, |
|
3, |
|
5 |
|
], |
|
[ |
|
1, |
|
3, |
|
5 |
|
] |
|
], |
|
"upsample_rates_decoder": [ |
|
8, |
|
8, |
|
2, |
|
2 |
|
], |
|
"upsample_initial_channel_decoder": 512, |
|
"upsample_kernel_sizes_decoder": [ |
|
16, |
|
16, |
|
4, |
|
4 |
|
], |
|
"periods_multi_period_discriminator": [ |
|
2, |
|
3, |
|
5, |
|
7, |
|
11 |
|
], |
|
"use_sdp": true, |
|
"noise_scale": 1.0, |
|
"inference_noise_scale": 0.667, |
|
"length_scale": 1.0, |
|
"noise_scale_dp": 1.0, |
|
"inference_noise_scale_dp": 0.8, |
|
"max_inference_len": null, |
|
"init_discriminator": false, |
|
"use_spectral_norm_disriminator": false, |
|
"use_speaker_embedding": true, |
|
"num_speakers": 109, |
|
"speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--vits/speaker_ids.json", |
|
"d_vector_file": null, |
|
"speaker_embedding_channels": 256, |
|
"use_d_vector_file": false, |
|
"d_vector_dim": 0, |
|
"detach_dp_input": true, |
|
"use_language_embedding": false, |
|
"embedded_language_dim": 4, |
|
"num_languages": 0, |
|
"language_ids_file": null, |
|
"use_speaker_encoder_as_loss": false, |
|
"speaker_encoder_config_path": "", |
|
"speaker_encoder_model_path": "", |
|
"condition_dp_on_speaker": true, |
|
"freeze_encoder": false, |
|
"freeze_DP": false, |
|
"freeze_PE": false, |
|
"freeze_flow_decoder": false, |
|
"freeze_waveform_decoder": false, |
|
"encoder_sample_rate": null, |
|
"interpolate_z": true, |
|
"reinit_DP": false, |
|
"reinit_text_encoder": false |
|
}, |
|
"lr_gen": 0.0002, |
|
"lr_disc": 0.0002, |
|
"lr_scheduler_gen": "ExponentialLR", |
|
"lr_scheduler_gen_params": { |
|
"gamma": 0.999875, |
|
"last_epoch": -1 |
|
}, |
|
"lr_scheduler_disc": "ExponentialLR", |
|
"lr_scheduler_disc_params": { |
|
"gamma": 0.999875, |
|
"last_epoch": -1 |
|
}, |
|
"kl_loss_alpha": 1.0, |
|
"disc_loss_alpha": 1.0, |
|
"gen_loss_alpha": 1.0, |
|
"feat_loss_alpha": 1.0, |
|
"mel_loss_alpha": 45.0, |
|
"dur_loss_alpha": 1.0, |
|
"speaker_encoder_loss_alpha": 1.0, |
|
"return_wav": true, |
|
"use_weighted_sampler": false, |
|
"weighted_sampler_attrs": {}, |
|
"weighted_sampler_multipliers": {}, |
|
"r": 1, |
|
"num_speakers": 0, |
|
"use_speaker_embedding": false, |
|
"speakers_file": "/Users/drew/Library/Application Support/tts/tts_models--en--vctk--vits/speaker_ids.json", |
|
"speaker_embedding_channels": 256, |
|
"language_ids_file": null, |
|
"use_language_embedding": false, |
|
"use_d_vector_file": false, |
|
"d_vector_file": null, |
|
"d_vector_dim": 0 |
|
} |