{
    "data": {
        "sampling_rate": 32000,
        "filter_length": 2048,
        "hop_length": 640,
        "win_length": 2048
    },
    "model": {
        "inter_channels": 192,
        "hidden_channels": 192,
        "filter_channels": 768,
        "n_heads": 2,
        "n_layers": 6,
        "kernel_size": 3,
        "p_dropout": 0.0,
        "resblock": "1",
        "resblock_kernel_sizes": [
            3,
            7,
            11
        ],
        "resblock_dilation_sizes": [
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ]
        ],
        "upsample_rates": [
            10,
            8,
            2,
            2,
            2
        ],
        "upsample_initial_channel": 768,
        "upsample_kernel_sizes": [
            20,
            16,
            8,
            2,
            2
        ],
        "gin_channels": 1024
    }
}