config.json

{
  "format": "vtx-tts",
  "train": {
    "segment_size": 16384
  },
  "data": {
    "text_cleaners": [],
    "max_wav_value": 32768.0,
    "sampling_rate": 24000,
    "filter_length": 1024,
    "hop_length": 256,
    "win_length": 1024,
    "n_mel_channels": 80,
    "mel_fmin": 0.0,
    "mel_fmax": 12000.0,
    "add_blank": true,
    "n_speakers": 0,
    "cleaned_text": true
  },
  "model": {
    "inter_channels": 192,
    "hidden_channels": 96,
    "filter_channels": 768,
    "n_heads": 2,
    "n_layers": 3,
    "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": [
      8,
      8,
      2,
      2
    ],
    "upsample_initial_channel": 320,
    "upsample_kernel_sizes": [
      16,
      16,
      4,
      4
    ],
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "use_sdp": false,
    "inference_only": false
  }
}