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

    // Features used for model training
    "use_mel": true,
    "use_audio": true,
    "use_frame_pitch": true
  },
  "model": {
    "generator": "nsfhifigan",
    "nsfhifigan": {
      "resblock": "1",
      "harmonic_num": 8,
      "upsample_rates": [
        8,
        4,
        2,
        2,
        2
      ],
      "upsample_kernel_sizes": [
        16,
        8,
        4,
        4,
        4
      ],
      "upsample_initial_channel": 768,
      "resblock_kernel_sizes": [
        3,
        7,
        11
      ],
      "resblock_dilation_sizes": [
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ],
        [
          1,
          3,
          5
        ]
      ]
    },
    "mpd": {
      "mpd_reshapes": [
        2,
        3,
        5,
        7,
        11,
        17,
        23,
        37
      ],
      "use_spectral_norm": false,
      "discriminator_channel_multi": 1
    }
  },
  "train": {
    "criterions": [
        "feature",
        "discriminator",
        "generator",
        "mel",
    ]
  },
  "inference": {
    "batch_size": 1,
  }
}