fast-speech_config.json

{
    "output_path": "/home/twbgmy/play/TTS-play/TTS/recipes/catotron",
    "logger_uri": null,
    "run_name": "fast_pitch_ljspeech",
    "project_name": null,
    "run_description": "\ud83d\udc38Coqui trainer run.",
    "print_step": 50,
    "plot_step": 100,
    "model_param_stats": false,
    "wandb_entity": null,
    "dashboard_logger": "tensorboard",
    "log_model_step": null,
    "save_step": 10000,
    "save_n_checkpoints": 5,
    "save_checkpoints": true,
    "save_all_best": false,
    "save_best_after": 1000,
    "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": false,
    "epochs": 1000,
    "batch_size": 16,
    "eval_batch_size": 16,
    "grad_clip": 5.0,
    "scheduler_after_epoch": true,
    "lr": 0.0001,
    "optimizer": "Adam",
    "optimizer_params": {
        "betas": [
            0.9,
            0.998
        ],
        "weight_decay": 1e-06
    },
    "lr_scheduler": "NoamLR",
    "lr_scheduler_params": {
        "warmup_steps": 4000
    },
    "use_grad_scaler": false,
    "cudnn_enable": true,
    "cudnn_deterministic": false,
    "cudnn_benchmark": false,
    "training_seed": 54321,
    "model": "fast_pitch",
    "num_loader_workers": 8,
    "num_eval_loader_workers": 4,
    "use_noise_augment": false,
    "audio": {
        "fft_size": 1024,
        "win_length": 1024,
        "hop_length": 256,
        "frame_shift_ms": null,
        "frame_length_ms": null,
        "stft_pad_mode": "reflect",
        "sample_rate": 22050,
        "resample": false,
        "preemphasis": 0.0,
        "ref_level_db": 20,
        "do_sound_norm": false,
        "log_func": "np.log",
        "do_trim_silence": true,
        "trim_db": 60.0,
        "do_rms_norm": false,
        "db_level": null,
        "power": 1.5,
        "griffin_lim_iters": 60,
        "num_mels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": 8000,
        "spec_gain": 1.0,
        "do_amp_to_db_linear": true,
        "do_amp_to_db_mel": true,
        "pitch_fmax": 640.0,
        "pitch_fmin": 0.0,
        "signal_norm": false,
        "min_level_db": -100,
        "symmetric_norm": true,
        "max_norm": 4.0,
        "clip_norm": true,
        "stats_path": null
    },
    "use_phonemes": false,
    "phonemizer": null,
    "phoneme_language": "ca-es",
    "compute_input_seq_cache": true,
    "text_cleaner": "multilingual_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": "_",
        "eos": "*",
        "bos": "^",
        "blank": null,
        "characters": "A\u00c0\u00c1BC\u00c7DE\u00c9\u00c8FGHI\u00cd\u00cfJKLMNO\u00d3\u00d2PQRSTU\u00dc\u00daVWXYZa\u00e0\u00e1bc\u00e7de\u00e9\u00e8fghi\u00ed\u00efjklmno\u00f3\u00f2pqrstu\u00fc\u00favwxyz",
        "punctuations": "!'(),-.:;?\u00b7 ",
        "phonemes": "",
        "is_unique": true,
        "is_sorted": true
    },
    "add_blank": false,
    "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": true,
    "compute_linear_spec": false,
    "precompute_num_workers": 4,
    "start_by_longest": false,
    "datasets": [
        {
            "name": "custom_turkish",
            "path": "/home/twbgmy/play/TTS-play/TTS/recipes/catotron/upc_ona",
            "meta_file_train": "upc_ona_train.txt",
            "ignored_speakers": null,
            "language": "",
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        },
        {
            "name": "custom_turkish",
            "path": "/home/twbgmy/play/TTS-play/TTS/recipes/catotron/upc_ona",
            "meta_file_train": "upc_ona_val.txt",
            "ignored_speakers": null,
            "language": "",
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        }
    ],
    "test_sentences": [
        "Hola Barcelona!",
        "Escriviu al text."
    ],
    "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,
    "base_model": "forward_tts",
    "model_args": {
        "num_chars": 89,
        "out_channels": 80,
        "hidden_channels": 384,
        "use_aligner": true,
        "use_pitch": true,
        "pitch_predictor_hidden_channels": 256,
        "pitch_predictor_kernel_size": 3,
        "pitch_predictor_dropout_p": 0.1,
        "pitch_embedding_kernel_size": 3,
        "duration_predictor_hidden_channels": 256,
        "duration_predictor_kernel_size": 3,
        "duration_predictor_dropout_p": 0.1,
        "positional_encoding": true,
        "poisitonal_encoding_use_scale": true,
        "length_scale": 1,
        "encoder_type": "fftransformer",
        "encoder_params": {
            "hidden_channels_ffn": 1024,
            "num_heads": 1,
            "num_layers": 6,
            "dropout_p": 0.1
        },
        "decoder_type": "fftransformer",
        "decoder_params": {
            "hidden_channels_ffn": 1024,
            "num_heads": 1,
            "num_layers": 6,
            "dropout_p": 0.1
        },
        "detach_duration_predictor": false,
        "max_duration": 75,
        "num_speakers": 1,
        "use_speaker_embedding": false,
        "speakers_file": null,
        "use_d_vector_file": false,
        "d_vector_dim": null,
        "d_vector_file": null
    },
    "num_speakers": 0,
    "speakers_file": null,
    "use_speaker_embedding": false,
    "use_d_vector_file": false,
    "d_vector_file": false,
    "d_vector_dim": 0,
    "spec_loss_type": "mse",
    "duration_loss_type": "mse",
    "use_ssim_loss": true,
    "ssim_loss_alpha": 1.0,
    "spec_loss_alpha": 1.0,
    "aligner_loss_alpha": 1.0,
    "pitch_loss_alpha": 0.1,
    "dur_loss_alpha": 0.1,
    "binary_align_loss_alpha": 0.1,
    "binary_loss_warmup_epochs": 150,
    "min_seq_len": 13,
    "max_seq_len": 500000,
    "r": 1,
    "f0_cache_path": "/home/twbgmy/play/TTS-play/TTS/recipes/catotron/f0_cache",
    "restore_path": "/home/twbgmy/.local/share/tts/tts_models--en--ljspeech--fast_pitch/model_file.pth",
    "github_branch": "* dev"
}