TTS/config.json

{
    "model_name": "TTS-phoneme",
    "model_description": "Training with phonemes created by phonemizer.",

    "audio":{
        "audio_processor": "audio",     // to use dictate different audio processors, if available.
        // Audio processing parameters
        "num_mels": 80,         // size of the mel spec frame. 
        "num_freq": 1025,       // number of stft frequency levels. Size of the linear spectogram frame.
        "sample_rate": 16000,   // wav sample-rate. If different than the original data, it is resampled.
        "frame_length_ms": 50,  // stft window length in ms.
        "frame_shift_ms": 12.5, // stft window hop-lengh in ms.
        "preemphasis": 0.97,    // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
        "min_level_db": -100,   // normalization range
        "ref_level_db": 20,     // reference level db, theoretically 20db is the sound of air.
        "power": 1.5,           // value to sharpen wav signals after GL algorithm.
        "griffin_lim_iters": 60,// #griffin-lim iterations. 30-60 is a good range. Larger the value, slower the generation.
        // Normalization parameters
        "signal_norm": true,    // normalize the spec values in range [0, 1]
        "symmetric_norm": false, // move normalization to range [-1, 1]
        "max_norm": 1,          // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
        "clip_norm": true,      // clip normalized values into the range.
        "mel_fmin": null,         // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
        "mel_fmax": null,        // maximum freq level for mel-spec. Tune for dataset!!
        "do_trim_silence": true  // enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
    },

    "embedding_size": 256,  // Character embedding vector length. You don't need to change it in general.
    "text_cleaner": "phoneme_cleaners",
    "epochs": 1000,         // total number of epochs to train.
    "lr": 0.001,            // Initial learning rate. If Noam decay is active, maximum learning rate.
    "lr_decay": false,      // if true, Noam learning rate decaying is applied through training.
    "warmup_steps": 4000,   // Noam decay steps to increase the learning rate from 0 to "lr"

    "batch_size": 32,       // Batch size for training. Lower values than 32 might cause hard to learn attention.
    "eval_batch_size":32,   
    "r": 5,                 // Number of frames to predict for step.
    "wd": 0.000001,         // Weight decay weight.
    "checkpoint": true,     // If true, it saves checkpoints per "save_step"
    "save_step": 5000,      // Number of training steps expected to save traning stats and checkpoints.
    "print_step": 10,       // Number of steps to log traning on console.
    "tb_model_param_stats": true,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging. 

    "run_eval": true,
    "data_path": "../../Data/LJSpeech-1.1/",  // DATASET-RELATED: can overwritten from command argument
    "meta_file_train": "transcript_train.txt",      // DATASET-RELATED: metafile for training dataloader.
    "meta_file_val": "transcript_val.txt",    // DATASET-RELATED: metafile for evaluation dataloader.
    "dataset": "tweb",      // DATASET-RELATED: one of TTS.dataset.preprocessors depending on your target dataset. Use "tts_cache" for pre-computed dataset by extract_features.py
    "min_seq_len": 0,       // DATASET-RELATED: minimum text length to use in training
    "max_seq_len": 300,     // DATASET-RELATED: maximum text length
    "output_path": "/media/erogol/data_ssd/Data/models/tweb_models/",      // DATASET-RELATED: output path for all training outputs.
    "num_loader_workers": 8,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
    "num_val_loader_workers": 4     // number of evaluation data loader processes.
}