config_v1.json

{
    "resblock": "1",
    "num_gpus": 0,
    "batch_size": 16,
    "learning_rate": 0.0002,
    "adam_b1": 0.8,
    "adam_b2": 0.99,
    "lr_decay": 0.999,
    "seed": 1234,

    "upsample_rates": [8,8],
    "upsample_kernel_sizes": [16,16],
    "upsample_initial_channel": 512,
    "resblock_kernel_sizes": [3,7,11],
    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
    "gen_istft_n_fft": 1024,
    "gen_istft_hop_size": 256,

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

    "sampling_rate": 22050,

    "fmin": 0,
    "fmax": 8000,
    "fmax_for_loss": null,

    "combd": {
        "combd_h_u" : [
            [16, 64, 256, 1024, 1024, 1024],
            [16, 64, 256, 1024, 1024, 1024],
            [16, 64, 256, 1024, 1024, 1024]
        ],
        "combd_d_k" : [
            [7, 11, 11, 11, 11, 5],
            [11, 21, 21, 21, 21, 5],
            [15, 41, 41, 41, 41, 5]
        ],
        "combd_d_s" : [
            [1, 1, 4, 4, 4, 1],
            [1, 1, 4, 4, 4, 1],
            [1, 1, 4, 4, 4, 1]
        ],
        "combd_d_d" : [
            [1, 1, 1, 1, 1, 1],
            [1, 1, 1, 1, 1, 1],
            [1, 1, 1, 1, 1, 1]
        ],
        "combd_d_g" : [
            [1, 4, 16, 64, 256, 1],
            [1, 4, 16, 64, 256, 1],
            [1, 4, 16, 64, 256, 1]
        ],
        "combd_d_p" : [
            [3, 5, 5, 5, 5, 2],
            [5, 10, 10, 10, 10, 2],
            [7, 20, 20, 20, 20, 2]
        ],

        "combd_op_f" : [1, 1, 1],
        "combd_op_k" : [3, 3, 3],
        "combd_op_g" : [1, 1, 1]
    },

    "sbd": {
        "use_sbd": true,
        "sbd_filters": [[64, 128, 256, 256, 256],[64, 128, 256, 256, 256],[64, 128, 256, 256, 256],[32, 64, 128, 128, 128]],
        "sbd_strides": [[1, 1, 3, 3, 1], [1, 1, 3, 3, 1], [1, 1, 3, 3, 1], [1, 1, 3, 3, 1]],
        "sbd_kernel_sizes": [
            [[7, 7, 7],[7, 7, 7],[7, 7, 7],[7, 7, 7],[7, 7, 7]],
            [[5, 5, 5],[5, 5, 5],[5, 5, 5],[5, 5, 5],[5, 5, 5]],
            [[3, 3, 3],[3, 3, 3],[3, 3, 3],[3, 3, 3],[3, 3, 3]],
            [[5, 5, 5],[5, 5, 5],[5, 5, 5],[5, 5, 5],[5, 5, 5]]
        ],
        "sbd_dilations": [
            [[5, 7, 11], [5, 7, 11], [5, 7, 11], [5, 7, 11], [5, 7, 11]],
            [[3, 5, 7], [3, 5, 7], [3, 5, 7], [3, 5, 7], [3, 5, 7]],
            [[1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3], [1, 2, 3]],
            [[1, 2, 3], [1, 2, 3], [1, 2, 3], [2, 3, 5], [2, 3, 5]]
        ],
        "sbd_band_ranges": [[0, 6], [0, 11], [0, 16], [0, 64]],
        "sbd_transpose": [false, false, false, true],
        "pqmf_config": {
            "sbd": [16, 256, 0.03, 10.0],
            "fsbd": [64, 256, 0.1, 9.0]
        },
        "segment_size": 8192
    },
    "pqmf_config": {
        "lv1": [2, 256, 0.25, 10.0],
        "lv2": [4, 192, 0.13, 10.0]
    },

    "projection_filters": [0, 1, 1, 1],
    "projection_kernels": [0, 5, 7, 11],

    "use_mrsd": true,

    "num_workers": 4,

    "dist_config": {
        "dist_backend": "nccl",
        "dist_url": "tcp://localhost:6000",
        "world_size": 1
    }
    
}