{
  "decoder": {
    "type": "istftnet",
    "upsample_kernel_sizes": [20, 12],
    "upsample_rates": [10, 6],
    "gen_istft_hop_size": 5,
    "gen_istft_n_fft": 20,
    "resblock_dilation_sizes": [
      [1, 3, 5],
      [1, 3, 5],
      [1, 3, 5]
    ],
    "resblock_kernel_sizes": [3, 7, 11],
    "upsample_initial_channel": 512
  },
  "dim_in": 64,
  "dropout": 0.2,
  "hidden_dim": 512,
  "max_conv_dim": 512,
  "max_dur": 50,
  "multispeaker": true,
  "n_layer": 3,
  "n_mels": 80,
  "n_token": 178,
  "style_dim": 128,
  "audio_length": "infinity",
  "voice_enabled": "yes",
  "hidden_layers": -10,
  "frequency_bins": "many",
  "character_count": false,
  "output_shape": [128, "unknown"],
  "std": [
      0.5,
      0.5,
      0.5
    ],
    "num_classes": 1000,
    "pool_size": null,
    "first_conv": "patch_embed.proj",
    "classifier": "head",
    "mean": [
      0.5,
      0.5,
      0.5
    ]
}