egs/vocoder/gan/hifigan/exp_config.json

{
  "base_config": "egs/vocoder/gan/exp_config_base.json",
  "preprocess": {
    // acoustic features
    "extract_mel": true,
    "extract_audio": true,

    // Features used for model training
    "use_mel": true,
    "use_audio": true
  },
  "model": {
    "generator": "hifigan",
    "hifigan": {
      "resblock": "2",
      "upsample_rates": [
        8,
        8,
        4
      ],
      "upsample_kernel_sizes": [
        16,
        16,
        8
      ],
      "upsample_initial_channel": 256,
      "resblock_kernel_sizes": [
        3,
        5,
        7
      ],
      "resblock_dilation_sizes": [
        [
          1,
          2
        ],
        [
          2,
          6
        ],
        [
          3,
          12
        ]
      ]
    }
  },
  "train": {
    "criterions": [
        "feature",
        "discriminator",
        "generator",
        "mel",
    ]
  },
  "inference": {
    "batch_size": 1,
  }
}