{ "output_path": "./output_Sourashtra_Female_tamil", "logger_uri": null, "run_name": "vits_Sourashtra_Female_tamil", "project_name": null, "run_description": "\ud83d\udc38Coqui trainer run.", "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": 7, "save_checkpoints": true, "save_all_best": false, "save_best_after": 0, "target_loss": null, "print_eval": true, "test_delay_epochs": -1, "run_eval": true, "run_eval_steps": null, "distributed_backend": "nccl", "distributed_url": "tcp://localhost:54321", "mixed_precision": true, "precision": "fp16", "epochs": 500, "batch_size": 16, "eval_batch_size": 8, "grad_clip": [ 1000, 1000 ], "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": null, "lr_scheduler_params": {}, "use_grad_scaler": false, "allow_tf32": false, "cudnn_enable": true, "cudnn_deterministic": false, "cudnn_benchmark": false, "training_seed": 54321, "model": "vits", "num_loader_workers": 8, "num_eval_loader_workers": 4, "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 }, "model_args": { "num_chars": 83, "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, "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 }, "_supports_cloning": false, "use_phonemes": false, "phonemizer": null, "phoneme_language": "en-us", "compute_input_seq_cache": true, "text_cleaner": "multilingual_cleaners", "enable_eos_bos_chars": false, "test_sentences_file": "", "phoneme_cache_path": "./output_Sourashtra_Female_tamil/phoneme_cache", "characters": { "characters_class": "TTS.tts.models.vits.VitsCharacters", "vocab_dict": null, "pad": "", "eos": "", "bos": "", "blank": "", "characters": " !(),-/1234?\u00b2\u00b3\u02bc\u0b83\u0b85\u0b86\u0b87\u0b88\u0b89\u0b8a\u0b8e\u0b8f\u0b90\u0b92\u0b93\u0b94\u0b95\u0b99\u0b9a\u0b9c\u0b9e\u0b9f\u0ba3\u0ba4\u0ba8\u0ba9\u0baa\u0bae\u0baf\u0bb0\u0bb1\u0bb2\u0bb3\u0bb4\u0bb5\u0bb6\u0bb7\u0bb8\u0bb9\u0bbe\u0bbf\u0bc0\u0bc1\u0bc2\u0bc6\u0bc7\u0bc8\u0bca\u0bcb\u0bcc\u0bcd\u0be7\u0bee\u200c\u2074\ua8d2", "punctuations": "!\u00a1'(),-.:;\u00bf? ", "phonemes": null, "is_unique": true, "is_sorted": true }, "add_blank": true, "batch_group_size": 3, "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": "./", "meta_file_train": "sourashtra_dataset_female/processed/processed_female_tamil_ljspeech.csv", "ignored_speakers": null, "language": "", "phonemizer": "", "meta_file_val": "", "meta_file_attn_mask": "" } ], "test_sentences": [ [ "\u0b92\u0b9c\u0ba9\u0bbe\u0b95\u0bcd \u0b92\u0b9c\u0ba9\u0bca \u0bae\u0bca\u0ba9\u0bcd\u0ba9\u0bc1 \u0bb8\u0bcd\u0baa\u0bbe4\u0bb5\u0bcd \u0b9c\u0ba9\u0bcd\u0bb2\u0ba9\u0bcd \u0bb6\u0bc6\u0b95\u0bcd\u0b95\u0bb8\u0bcd\u0ba4\u0bca \u0bb9\u0bca\u0baf\u0bc6 \u0b9c\u0bc12\u0b95\u0bc13 \u0b95\u0bbe\u0bb0\u0ba3\u0bbe\u0ba9\u0bc1\u0bae\u0bcd \u0b8e\u0bb2\u0bcd\u0baf\u0bca \u0b92\u0ba3\u0bcd\u0b9f\u0bcd\u0baf \u0b95\u0bbe\u0bb0\u0ba3\u0bca\u0b95\u0ba9\u0bbf \u0bb8\u0bc7 \u0bae\u0bc6\u0ba9\u0bbf \u0b85\u0bae\u0bbf \u0b95\u0bb3\u0bc8\u0bb2\u0bbf\u0bb0\u0bbf\u0baf\u0bca \u0ba4\u0bc6\u0bb2\u0bcd\u0baf\u0b95 \u0bb9\u0bbe\u0bb2\u0bcd \u0b9a\u0bca\u0b95\u0bcd\u0b95\u0b9f\u0bc13\u0bb8\u0bcd", "Sourashtra_Female_Tamil", null, "ta" ] ], "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, "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, "github_branch": "inside_docker" }