{
  "train": {
    "log_interval": 50,
    "eval_interval": 800,
    "seed": 1234,
    "epochs": 10000,
    "learning_rate": 0.0001,
    "betas": [
      0.8,
      0.99
    ],
    "eps": 1e-09,
    "batch_size": 19,
    "fp16_run": false,
    "lr_decay": 0.999875,
    "segment_size": 10240,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0,
    "use_sr": true,
    "max_speclen": 512,
    "port": "8001",
    "keep_ckpts": 3,
    "fft_sizes": [
      384,
      683,
      171
    ],
    "hop_sizes": [
      30,
      60,
      10
    ],
    "win_lengths": [
      150,
      300,
      60
    ],
    "window": "hann_window"
  },
  "data": {
    "training_files": "filelists/44k/train.txt",
    "validation_files": "filelists/44k/val.txt",
    "max_wav_value": 32768.0,
    "sampling_rate": 44100,
    "filter_length": 2048,
    "hop_length": 512,
    "win_length": 2048,
    "n_mel_channels": 80,
    "mel_fmin": 0.0,
    "mel_fmax": 22050
  },
  "model": {
    "inter_channels": 192,
    "hidden_channels": 192,
    "filter_channels": 768,
    "n_heads": 2,
    "n_layers": 6,
    "kernel_size": 3,
    "p_dropout": 0.1,
    "resblock": "1",
    "resblock_kernel_sizes": [
      3,
      7,
      11
    ],
    "resblock_dilation_sizes": [
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ],
      [
        1,
        3,
        5
      ]
    ],
    "upsample_rates": [
      4,
      4
    ],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [
      16,
      16
    ],
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "gin_channels": 256,
    "ssl_dim": 256,
    "n_speakers": 200,
    "type_": "mb-istft",
    "gen_istft_n_fft": 16,
    "gen_istft_hop_size": 4,
    "subbands": 8
  },
  "spk": {
    "kiritan": 0
  }
}