config.json

{
  "output_path": "/kaggle/working/",
  "logger_uri": null,
  "run_name": "vits_4_nov",
  "project_name": null,
  "run_description": "\ud83d\udc38Coqui trainer run.",
  "print_step": 100,
  "plot_step": 100,
  "model_param_stats": false,
  "wandb_entity": null,
  "dashboard_logger": "tensorboard",
  "save_on_interrupt": true,
  "log_model_step": null,
  "save_step": 500,
  "save_n_checkpoints": 1,
  "save_checkpoints": true,
  "save_all_best": false,
  "save_best_after": 100,
  "target_loss": null,
  "print_eval": false,
  "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": 50,
  "batch_size": 8,
  "eval_batch_size": 4,
  "grad_clip": [1000.0, 1000.0],
  "scheduler_after_epoch": true,
  "lr": 0.0001,
  "optimizer": "AdamW",
  "optimizer_params": {
    "betas": [0.8, 0.99],
    "eps": 1e-9,
    "weight_decay": 0.01
  },
  "lr_scheduler": "",
  "lr_scheduler_params": null,
  "use_grad_scaler": false,
  "allow_tf32": false,
  "cudnn_enable": true,
  "cudnn_deterministic": false,
  "cudnn_benchmark": true,
  "training_seed": 54321,
  "model": "vits",
  "num_loader_workers": 4,
  "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
  },
  "use_phonemes": false,
  "phonemizer": null,
  "phoneme_language": null,
  "compute_input_seq_cache": true,
  "text_cleaner": null,
  "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": "\u0964",
    "bos": "<BOS>",
    "blank": "<BLNK>",
    "characters": "\u0987\u0997\u0982\u09bc\u2019\u09c1\u0983\u09a8\u09e7\u099d\u09c2\u0993\u2018\u098a\u09cb\u099b\u09aa\u09ab\u09c8\u09ee\u09b7\u09af\u09ce\u09a2\u0988\u0995\u09a0\u09bf\u099c\u09e6\u09ec\u09c0\u099f\u09a1\u098f\u0985\u098b\u09a7\u099a\u09c7\u09e8\u09e9\u09a3\u0989\u09df\u09dd\u0996\u09b2\u09ad\u09d7\u09b8\u09b9\u09cd\u09dc\u09a6\u09a5\u09ac\u0994\u09be\u099e\u09b6\u09b0\u09cc\u09ae\u2014\u0990\u0986\u09c3\u0998\u0999\u200c\u0981\u09ea\u09eb\u09a4",
    "punctuations": ".?-!|, ",
    "phonemes": null,
    "is_unique": true,
    "is_sorted": true
  },
  "add_blank": true,
  "batch_group_size": 0,
  "loss_masking": null,
  "min_audio_len": 1,
  "max_audio_len": null,
  "min_text_len": 1,
  "max_text_len": null,
  "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": "/kaggle/input/datahrbn/MyTTSDataset",
      "meta_file_train": "/kaggle/input/datahrbn/MyTTSDataset/metadata.txt",
      "ignored_speakers": null,
      "language": "",
      "phonemizer": "",
      "meta_file_val": "",
      "meta_file_attn_mask": ""
    }
  ],
  "test_sentences": [
    [
      "\u0987\u09df\u09be\u09b9\u09c1\u09a6,\u09a8\u09df,\u09ac\u09cd\u09af\u09df,\u0987\u09df\u09be\u09b9\u09c1\u09a6\u09c0,\u09a8\u09c7\u0993\u09df\u09be,\u0989\u09ad\u09df\u09c7,\u09af\u09be\u09df,\u09b9\u09df\u09c7\u099b\u09bf\u09b2,\u09aa\u09cd\u09b0\u09df\u09cb\u099c\u09a8\u0964"
    ]
  ],
  "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": 86,
    "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": 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": null,
  "weighted_sampler_multipliers": null,
  "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": "/kaggle/input/ttsbng/transformers/default/1/model_file.pth",
  "github_branch": "inside_docker"
}