config.json

{
    "train": {
        "learning_rate": 2e-4,
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-9,
        "lr_decay": 0.999875,
        "segment_size": 8192,
        "c_mel": 45,
        "c_kl": 1.0
    },
    "data": {
        "vocab_size": 256,
        "max_wav_value": 32768.0,
        "sampling_rate": 16000,
        "filter_length": 1024,
        "hop_length": 256,
        "win_length": 1024,
        "n_mel_channels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": null
    },
    "model": {
        "inter_channels": 192,
        "hidden_channels": 192,
        "filter_channels": 768,
        "n_heads": 2,
        "n_layers": 6,
        "kernel_size": 3,
        "p_dropout": 0.1,
        "resblock": "1",
        "resblock_kernel_sizes": [
            3,
            7,
            11
        ],
        "resblock_dilation_sizes": [
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ]
        ],
        "upsample_rates": [
            8,
            8,
            2,
            2
        ],
        "upsample_initial_channel": 512,
        "upsample_kernel_sizes": [
            16,
            16,
            4,
            4
        ],
        "n_layers_q": 3,
        "use_spectral_norm": false
    }
}