| { | |
| "output_path": "/kaggle/working/train_output", | |
| "logger_uri": null, | |
| "run_name": "vits_fa_female", | |
| "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", | |
| "log_model_step": 1000, | |
| "save_step": 1000, | |
| "save_n_checkpoints": 5, | |
| "save_checkpoints": true, | |
| "save_all_best": false, | |
| "save_best_after": 10000, | |
| "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": false, | |
| "epochs": 1000, | |
| "batch_size": 8, | |
| "eval_batch_size": 4, | |
| "grad_clip": [ | |
| 1000.0, | |
| 1000.0 | |
| ], | |
| "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": null, | |
| "lr_scheduler_params": {}, | |
| "use_grad_scaler": false, | |
| "cudnn_enable": true, | |
| "cudnn_deterministic": false, | |
| "cudnn_benchmark": false, | |
| "training_seed": 54321, | |
| "model": "vits", | |
| "num_loader_workers": 0, | |
| "num_eval_loader_workers": 2, | |
| "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": "fa", | |
| "compute_input_seq_cache": true, | |
| "text_cleaner": "basic_cleaners", | |
| "enable_eos_bos_chars": false, | |
| "test_sentences_file": "", | |
| "phoneme_cache_path": "/kaggle/working/train_output/phoneme_cache", | |
| "characters": { | |
| "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes", | |
| "vocab_dict": null, | |
| "pad": "<PAD>", | |
| "eos": "<EOS>", | |
| "bos": "<BOS>", | |
| "blank": "<BLNK>", | |
| "characters": "\u02c8\u02cc\u02d0\u02d1pbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029faegiouwy\u026a\u028a\u0329\u00e6\u0251\u0254\u0259\u025a\u025b\u025d\u0268\u0303\u0289\u028c\u028d0123456789\"#$%*+/=ABCDEFGHIJKLMNOPRSTUVWXYZ[]^_{}", | |
| "punctuations": "!(),-.:;? \u0320\u060c\u061b\u061f\u200c<>", | |
| "phonemes": "\u02c8\u02cc\u02d0\u02d1pbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029faegiouwy\u026a\u028a\u0329\u00e6\u0251\u0254\u0259\u025a\u025b\u025d\u0268\u0303\u0289\u028c\u028d0123456789\"#$%*+/=ABCDEFGHIJKLMNOPRSTUVWXYZ[]^_{}", | |
| "is_unique": true, | |
| "is_sorted": true | |
| }, | |
| "add_blank": true, | |
| "batch_group_size": 5, | |
| "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": "mozilla_with_speaker", | |
| "dataset_name": "multi_persian", | |
| "path": "/kaggle/input", | |
| "meta_file_train": "metadata.csv", | |
| "ignored_speakers": null, | |
| "language": "fa", | |
| "phonemizer": "espeak", | |
| "meta_file_val": "", | |
| "meta_file_attn_mask": "" | |
| } | |
| ], | |
| "test_sentences": [ | |
| [ | |
| "\u0633\u0644\u0637\u0627\u0646 \u0645\u062d\u0645\u0648\u062f \u062f\u0631 \u0632\u0645\u0633\u062a\u0627\u0646\u06cc \u0633\u062e\u062a \u0628\u0647 \u0637\u0644\u062e\u06a9 \u06af\u0641\u062a \u06a9\u0647", | |
| "dilara", | |
| null, | |
| "fa" | |
| ], | |
| [ | |
| " \u0628\u0627 \u0627\u06cc\u0646 \u062c\u0627\u0645\u0647 \u06cc \u06cc\u06a9 \u0644\u0627 \u062f\u0631 \u0627\u06cc\u0646 \u0633\u0631\u0645\u0627 \u0686\u0647 \u0645\u06cc \u06a9\u0646\u06cc ", | |
| "farid", | |
| null, | |
| "fa" | |
| ], | |
| [ | |
| "\u0645\u0631\u062f\u06cc \u0646\u0632\u062f \u0628\u0642\u0627\u0644\u06cc \u0622\u0645\u062f \u0648 \u06af\u0641\u062a \u067e\u06cc\u0627\u0632 \u0647\u0645 \u062f\u0647 \u062a\u0627 \u062f\u0647\u0627\u0646 \u0628\u062f\u0627\u0646 \u062e\u0648 \u0634\u0628\u0648\u06cc \u0633\u0627\u0632\u0645.", | |
| "farid", | |
| null, | |
| "fa" | |
| ], | |
| [ | |
| "\u0627\u0632 \u0645\u0627\u0644 \u062e\u0648\u062f \u067e\u0627\u0631\u0647 \u0627\u06cc \u06af\u0648\u0634\u062a \u0628\u0633\u062a\u0627\u0646 \u0648 \u0632\u06cc\u0631\u0647 \u0628\u0627\u06cc\u06cc \u0645\u0639\u0637\u0651\u0631 \u0628\u0633\u0627\u0632", | |
| "dilara", | |
| null, | |
| "fa" | |
| ], | |
| [ | |
| "\u06cc\u06a9 \u0628\u0627\u0631 \u0647\u0645 \u0627\u0632 \u062c\u0647\u0646\u0645 \u0628\u06af\u0648\u06cc\u06cc\u062f.", | |
| "changiz", | |
| null, | |
| "fa" | |
| ], | |
| [ | |
| "\u06cc\u06a9\u06cc \u0627\u0633\u0628\u06cc \u0628\u0647 \u0639\u0627\u0631\u06cc\u062a \u062e\u0648\u0627\u0633\u062a", | |
| "changiz", | |
| null, | |
| "fa" | |
| ] | |
| ], | |
| "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": 156, | |
| "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": 10, | |
| "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": 1.0, | |
| "max_inference_len": null, | |
| "init_discriminator": true, | |
| "use_spectral_norm_disriminator": false, | |
| "use_speaker_embedding": false, | |
| "num_speakers": 0, | |
| "speakers_file": "train_output/kagg/speakers.pth", | |
| "d_vector_file": [ | |
| "/kaggle/working/speakers.pth" | |
| ], | |
| "speaker_embedding_channels": 256, | |
| "use_d_vector_file": true, | |
| "d_vector_dim": 512, | |
| "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": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/config_se.json", | |
| "speaker_encoder_model_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/model_se.pth.tar", | |
| "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": 9.0, | |
| "return_wav": true, | |
| "use_weighted_sampler": true, | |
| "weighted_sampler_attrs": { | |
| "speaker_name": 1.0 | |
| }, | |
| "weighted_sampler_multipliers": {}, | |
| "r": 1, | |
| "num_speakers": 0, | |
| "use_speaker_embedding": false, | |
| "speakers_file": "train_output/kagg/speakers.pth", | |
| "speaker_embedding_channels": 256, | |
| "language_ids_file": null, | |
| "use_language_embedding": false, | |
| "use_d_vector_file": true, | |
| "d_vector_file": [ | |
| "/kaggle/working/speakers.pth" | |
| ], | |
| "d_vector_dim": 512 | |
| } |