TTS/tests/inputs/test_vocoder_wavernn_config.json

{
    "run_name": "wavernn_test",
    "run_description": "wavernn_test training",

    // AUDIO PARAMETERS
    "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": 0.0,        // minimum freq level for mel-spec. ~50 for male and ~95 for female voices. Tune for dataset!!
        "mel_fmax": 8000.0,     // maximum freq level for mel-spec. Tune for dataset!!
        "spec_gain": 20.0,         // 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
    },

    // Generating / Synthesizing
    "batched": true,
    "target_samples": 11000,		// target number of samples to be generated in each batch entry
    "overlap_samples": 550,		// number of samples for crossfading between batches

    // DISTRIBUTED TRAINING
    // "distributed":{
    //     "backend": "nccl",
    //     "url": "tcp:\/\/localhost:54321"
    // },

    // MODEL PARAMETERS
    "use_aux_net": true,
    "use_upsample_net": true,
    "upsample_factors": [4, 8, 8],	// this needs to correctly factorise hop_length
    "seq_len": 1280,			// has to be devideable by hop_length
    "mode": "mold",         		// mold [string], gauss [string], bits [int]
    "mulaw": false,         		// apply mulaw if mode is bits
    "padding": 2,			// pad the input for resnet to see wider input length

    // GENERATOR - for backward compatibility
    "generator_model": "WaveRNN",

    // DATASET
    //"use_gta": true,				// use computed gta features from the tts model
    "data_path": "tests/data/ljspeech/wavs/",	// path containing training wav files
    "feature_path": null, 			// path containing computed features from wav files if null compute them

    // MODEL PARAMETERS
    "wavernn_model_params": {
        "rnn_dims": 512,
        "fc_dims": 512,
        "compute_dims": 128,
        "res_out_dims": 128,
        "num_res_blocks": 10,
        "use_aux_net": true,
        "use_upsample_net": true,
        "upsample_factors": [4, 8, 8] 	// this needs to correctly factorise hop_length
    },
    "mixed_precision": false,

    // TRAINING
    "batch_size": 4,       	// Batch size for training. Lower values than 32 might cause hard to learn attention.
    "epochs": 1,        	// total number of epochs to train.

    // VALIDATION
    "run_eval": true,
    "test_every_epochs": 10,         // Test after set number of epochs (Test every 20 epochs for example)

    // OPTIMIZER
    "grad_clip": 4,		     // 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": [200000, 400000, 600000]
    },
    "lr": 1e-4,			// initial learning rate

    // TENSORBOARD and LOGGING
    "print_step": 25,       // 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": 25000,      // 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": false,     // 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_val_loader_workers": 0,    // number of evaluation data loader processes.
    "eval_split_size": 10,	    // number of samples for testing

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