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

    // Features used for model training
    "use_mel": true,
    "use_audio": true,
    "use_amplitude_phase": true
  },
  "model": {
    "generator": "apnet",
    "apnet": {
      "ASP_channel": 512,
      "ASP_resblock_kernel_sizes": [3,7,11],
      "ASP_resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
      "ASP_input_conv_kernel_size": 7,
      "ASP_output_conv_kernel_size": 7,

      "PSP_channel": 512,
      "PSP_resblock_kernel_sizes": [3,7,11],
      "PSP_resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]], 
      "PSP_input_conv_kernel_size": 7,
      "PSP_output_R_conv_kernel_size": 7,
      "PSP_output_I_conv_kernel_size": 7,
    }
  },
  "train": {
    "criterions": [
        "feature",
        "discriminator",
        "generator",
        "mel",
        "phase",
        "amplitude",
        "consistency"
    ]
  },
  "inference": {
    "batch_size": 1,
  }
}