Model/Nene_Nanami_Rong_Tang/config.json

{
  "train": {
    "segment_size": 8192
  },
  "data": {
    "text_cleaners":["zh_ja_mixture_cleaners"],
    "max_wav_value": 32768.0,
    "sampling_rate": 22050,
    "filter_length": 1024,
    "hop_length": 256,
    "win_length": 1024,
    "add_blank": true,
    "n_speakers": 5
  },
  "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": [8,8,2,2],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [16,16,4,4],
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "gin_channels": 256
  },
  "speakers": ["\u7dbe\u5730\u5be7\u3005", "\u5728\u539f\u4e03\u6d77", "\u5c0f\u8338", "\u5510\u4e50\u541f"],
  "symbols": ["_", ",", ".", "!", "?", "-", "~", "\u2026", "A", "E", "I", "N", "O", "Q", "U", "a", "b", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "r", "s", "t", "u", "v", "w", "y", "z", "\u0283", "\u02a7", "\u02a6", "\u026f", "\u0279", "\u0259", "\u0265", "\u207c", "\u02b0", "`", "\u2192", "\u2193", "\u2191", " "]
}