vocoder/BigVGAN/bigvgan_audioset16khz_80band.json

{
    "resblock": "1",
    "num_gpus": 0,
    "batch_size": 32,
    "learning_rate": 0.0001,
    "adam_b1": 0.8,
    "adam_b2": 0.99,
    "lr_decay": 0.999,
    "seed": 1234,

    "upsample_rates": [4,4,2,2,2,2],
    "upsample_kernel_sizes": [8,8,4,4,4,4],
    "upsample_initial_channel": 1536,
    "resblock_kernel_sizes": [3,7,11],
    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],

    "activation": "snakebeta",
    "snake_logscale": true,

    "resolutions": [[1024, 120, 600], [2048, 240, 1200], [512, 50, 240]],
    "mpd_reshapes": [2, 3, 5, 7, 11],
    "use_spectral_norm": false,
    "discriminator_channel_mult": 1,

    "segment_size": 8192,
    "num_mels": 80,
    "num_freq": 1025,
    "n_fft": 1024,
    "hop_size": 256,
    "win_size": 1024,

    "sampling_rate": 16000,

    "fmin": 125,
    "fmax": 7600,
    "fmax_for_loss": null,

    "num_workers": 4,

    "dist_config": {
        "dist_backend": "nccl",
        "dist_url": "tcp://localhost:44327",
        "world_size": 1
    }
}