TTS/tests/inputs/test_vocoder_wavegrad.json

{
    "run_name": "wavegrad-ljspeech",
    "run_description": "wavegrad ljspeech",

    "audio":{
        "fft_size": 1024,         // number of stft frequency levels. Size of the linear spectogram frame.
        "win_length": 1024,      // stft window length in ms.
        "hop_length": 256,       // stft window hop-lengh in ms.
        "frame_length_ms": null, // stft window length in ms.If null, 'win_length' is used.
        "frame_shift_ms": null,  // stft window hop-lengh in ms. If null, 'hop_length' is used.

        // Audio processing parameters
        "sample_rate": 22050,   // DATASET-RELATED: wav sample-rate. If different than the original data, it is resampled.
        "preemphasis": 0.0,     // pre-emphasis to reduce spec noise and make it more structured. If 0.0, no -pre-emphasis.
        "ref_level_db": 0,     // reference level db, theoretically 20db is the sound of air.

        // Silence trimming
        "do_trim_silence": true,// enable trimming of slience of audio as you load it. LJspeech (false), TWEB (false), Nancy (true)
        "trim_db": 60,          // threshold for timming silence. Set this according to your dataset.

        // MelSpectrogram parameters
        "num_mels": 80,         // size of the mel spec frame.
        "mel_fmin": 50.0,        // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
        "mel_fmax": 7600.0,     // maximum freq level for mel-spec. Tune for dataset!!
        "spec_gain": 1.0,         // scaler value appplied after log transform of spectrogram.

        // Normalization parameters
        "signal_norm": true,    // normalize spec values. Mean-Var normalization if 'stats_path' is defined otherwise range normalization defined by the other params.
        "min_level_db": -100,   // lower bound for normalization
        "symmetric_norm": true, // move normalization to range [-1, 1]
        "max_norm": 4.0,        // scale normalization to range [-max_norm, max_norm] or [0, max_norm]
        "clip_norm": true,      // clip normalized values into the range.
        "stats_path": null      // DO NOT USE WITH MULTI_SPEAKER MODEL. scaler stats file computed by 'compute_statistics.py'. If it is defined, mean-std based notmalization is used and other normalization params are ignored
    },

    // DISTRIBUTED TRAINING
    "mixed_precision": false,
    "distributed":{
        "backend": "nccl",
        "url": "tcp:\/\/localhost:54322"
    },

    "target_loss": "avg_wavegrad_loss",  // loss value to pick the best model to save after each epoch

    // MODEL PARAMETERS
    "generator_model": "wavegrad",
    "model_params":{
        "y_conv_channels":32,
        "x_conv_channels":768,
        "ublock_out_channels": [512, 512, 256, 128, 128],
        "dblock_out_channels": [128, 128, 256, 512],
        "upsample_factors": [4, 4, 4, 2, 2],
        "upsample_dilations": [
            [1, 2, 1, 2],
            [1, 2, 1, 2],
            [1, 2, 4, 8],
            [1, 2, 4, 8],
            [1, 2, 4, 8]],
        "use_weight_norm": true
    },

    // DATASET
    "data_path": "tests/data/ljspeech/wavs/",  // root data path. It finds all wav files recursively from there.
    "feature_path": null,   // if you use precomputed features
    "seq_len": 6144,        // 24 * hop_length
    "pad_short": 0,      // additional padding for short wavs
    "conv_pad": 0,          // additional padding against convolutions applied to spectrograms
    "use_noise_augment": false,     // add noise to the audio signal for augmentation
    "use_cache": true,      // use in memory cache to keep the computed features. This might cause OOM.

    "reinit_layers": [],    // give a list of layer names to restore from the given checkpoint. If not defined, it reloads all heuristically matching layers.

    // TRAINING
    "batch_size": 1,      // Batch size for training.
    "train_noise_schedule":{
        "min_val": 1e-6,
        "max_val": 1e-2,
        "num_steps": 1000
    },
    "test_noise_schedule":{
        "min_val": 1e-6,
        "max_val": 1e-2,
        "num_steps": 2
    },

    // VALIDATION
    "run_eval": true,       // enable/disable evaluation run

    // OPTIMIZER
    "epochs": 1,                // total number of epochs to train.
    "grad_clip": 1.0,                 // Generator gradient clipping threshold. Apply gradient clipping if > 0
    "lr_scheduler": "MultiStepLR",  // one of the schedulers from https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
    "lr_scheduler_params": {
        "gamma": 0.5,
        "milestones": [100000, 200000, 300000, 400000, 500000, 600000]
    },
    "lr": 1e-4,                  // Initial learning rate. If Noam decay is active, maximum learning rate.

    // TENSORBOARD and LOGGING
    "print_step": 250,       // Number of steps to log traning on console.
    "print_eval": false,     // If True, it prints loss values for each step in eval run.
    "save_step": 10000,      // Number of training steps expected to plot training stats on TB and save model checkpoints.
    "checkpoint": true,     // If true, it saves checkpoints per "save_step"
    "keep_all_best": true,  // If true, keeps all best_models after keep_after steps
    "keep_after": 10000,    // Global step after which to keep best models if keep_all_best is true
    "tb_model_param_stats": true,     // true, plots param stats per layer on tensorboard. Might be memory consuming, but good for debugging.

    // DATA LOADING
    "num_loader_workers": 0,        // number of training data loader processes. Don't set it too big. 4-8 are good values.
    "num_eval_loader_workers": 0,    // number of evaluation data loader processes.
    "eval_split_size": 4,

    // PATHS
    "output_path": "tests/train_outputs/"
}