{
  "filter_channels": 768,
  "gin_channels": 256,
  "hidden_channels": 192,
  "inter_channels": 192,
  "kernel_size": 3,
  "n_heads": 2,
  "n_layers": 6,
  "n_layers_q": 3,
  "n_style": 8,
  "n_vocab": 85,
  "p_dropout": 0.1,
  "resblock": "1",
  "resblock_dilation_sizes": [
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ],
    [
      1,
      3,
      5
    ]
  ],
  "resblock_kernel_sizes": [
    3,
    7,
    11
  ],
  "segment_size": 32,
  "spec_channels": 513,
  "upsample_initial_channel": 512,
  "upsample_kernel_sizes": [
    16,
    16,
    4,
    4
  ],
  "upsample_rates": [
    8,
    8,
    2,
    2
  ],
  "use_spectral_norm": false,
  "weighted": true
}