| { | |
| "output_path": "voco_logs/", | |
| "logger_uri": null, | |
| "run_name": "voco-single", | |
| "project_name": "voco-single-female", | |
| "run_description": "voco-tts single female", | |
| "print_step": 50, | |
| "plot_step": 100, | |
| "model_param_stats": false, | |
| "wandb_entity": null, | |
| "dashboard_logger": "tensorboard", | |
| "save_on_interrupt": true, | |
| "log_model_step": null, | |
| "save_step": 5000, | |
| "save_n_checkpoints": 10, | |
| "save_checkpoints": true, | |
| "save_all_best": false, | |
| "save_best_after": 0, | |
| "target_loss": null, | |
| "print_eval": false, | |
| "test_delay_epochs": -1, | |
| "run_eval": false, | |
| "run_eval_steps": null, | |
| "distributed_backend": "nccl", | |
| "distributed_url": "tcp://localhost:54321", | |
| "mixed_precision": true, | |
| "precision": "fp16", | |
| "epochs": 1500, | |
| "batch_size": 16, | |
| "eval_batch_size": 16, | |
| "grad_clip": [ | |
| 5.0, | |
| 5.0 | |
| ], | |
| "scheduler_after_epoch": true, | |
| "lr": 5e-05, | |
| "optimizer": "AdamW", | |
| "optimizer_params": { | |
| "betas": [ | |
| 0.8, | |
| 0.99 | |
| ], | |
| "eps": 1e-09, | |
| "weight_decay": 0.01 | |
| }, | |
| "lr_scheduler": "ReduceROnPlateau", | |
| "lr_scheduler_params": { | |
| "mode": "min", | |
| "factor": 0.5, | |
| "patience": 5 | |
| }, | |
| "use_grad_scaler": false, | |
| "allow_tf32": false, | |
| "cudnn_enable": true, | |
| "cudnn_deterministic": false, | |
| "cudnn_benchmark": false, | |
| "training_seed": 54321, | |
| "model": "vits", | |
| "num_loader_workers": 12, | |
| "num_eval_loader_workers": 12, | |
| "use_noise_augment": true, | |
| "audio": { | |
| "fft_size": 1024, | |
| "sample_rate": 22050, | |
| "win_length": 1024, | |
| "hop_length": 256, | |
| "num_mels": 80, | |
| "mel_fmin": 0, | |
| "mel_fmax": null | |
| }, | |
| "use_phonemes": false, | |
| "phonemizer": null, | |
| "phoneme_language": null, | |
| "compute_input_seq_cache": false, | |
| "text_cleaner": "basic_cleaners", | |
| "enable_eos_bos_chars": false, | |
| "test_sentences_file": "", | |
| "phoneme_cache_path": null, | |
| "characters": { | |
| "characters_class": "TTS.tts.utils.text.characters.Graphemes", | |
| "vocab_dict": null, | |
| "pad": "<PAD>", | |
| "eos": "<EOS>", | |
| "bos": "<BOS>", | |
| "blank": "<BLNK>", | |
| "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u014a\u014b", | |
| "punctuations": "!'(),-.:;?\" ", | |
| "phonemes": null, | |
| "is_unique": false, | |
| "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": "ljspeech", | |
| "dataset_name": "", | |
| "path": "ones_data/", | |
| "meta_file_train": "wavs/metadata.csv", | |
| "ignored_speakers": null, | |
| "language": "", | |
| "phonemizer": "", | |
| "meta_file_val": "", | |
| "meta_file_attn_mask": "" | |
| } | |
| ], | |
| "test_sentences": [ | |
| [ | |
| "Abantu abasinga obungi tebamanyi kwogera bulungi Luganda." | |
| ], | |
| [ | |
| "Kabaka waffe yasiimye naggulawo e ddwaliro lya kookolo." | |
| ], | |
| [ | |
| "Minisita yasabye abakyala bonna okwegemesa ekirwadde." | |
| ], | |
| [ | |
| "Ennyanja yaffe egenda kusaanawo yonna singa gavumenti teteekamu maanyi." | |
| ] | |
| ], | |
| "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": 70, | |
| "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": 0.25, | |
| "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": 1.0, | |
| "max_inference_len": null, | |
| "init_discriminator": true, | |
| "use_spectral_norm_disriminator": false, | |
| "use_speaker_embedding": false, | |
| "num_speakers": 0, | |
| "speakers_file": null, | |
| "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": null, | |
| "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, | |
| "restore_path": "tts_models--en--ljspeech--vits/model_file.pth", | |
| "github_branch": "* dev" | |
| } |