configs/zero_japanese_base2.json

{
  "train": {
    "log_interval": 200,
    "eval_interval": 1000,
    "seed": 1234,
    "epochs": 10000,
    "learning_rate": 2e-4,
    "betas": [0.8, 0.99],
    "eps": 1e-9,
    "batch_size": 32,
    "fp16_run": true,
    "lr_decay": 0.999875,
    "segment_size": 8192,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0
  },
  "data": {
    "training_files":"filelists/zero_train_filelist.txt.cleaned",
    "validation_files":"filelists/zero_val_filelist.txt.cleaned",
    "text_cleaners":["japanese_cleaners2"],
    "max_wav_value": 32768.0,
    "sampling_rate": 22050,
    "filter_length": 1024,
    "hop_length": 256,
    "win_length": 1024,
    "n_mel_channels": 80,
    "mel_fmin": 0.0,
    "mel_fmax": null,
    "add_blank": true,
    "n_speakers": 21,
    "cleaned_text": true
  },
  "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": ["\u30eb\u30a4\u30ba", "\u30c6\u30a3\u30d5\u30a1\u30cb\u30a2", "\u30a4\u30eb\u30af\u30af\u30a5", "\u30a2\u30f3\u30ea\u30a8\u30c3\u30bf", "\u30bf\u30d0\u30b5", "\u30cf\u30eb\u30ca", "\u30ea\u30b7\u30e5", "\u30b7\u30a8\u30b9\u30bf", "\u30a2\u30ad\u30ca", "\u30af\u30ea\u30b9\u30c6\u30a3\u30ca", "\u30ab\u30c8\u30ec\u30a2", "\u30a8\u30ec\u30aa\u30ce\u30fc\u30eb", "\u30e2\u30f3\u30e2\u30e9\u30f3\u30b7\u30fc", "\u30ea\u30fc\u30f4\u30eb", "\u30ad\u30e5\u30eb\u30b1", "\u30a6\u30a7\u30b6\u30ea\u30fc", "\u30b5\u30a4\u30c8", "\u30ae\u30fc\u30b7\u30e5", "\u30b3\u30eb\u30d9\u30fc\u30eb", "\u30aa\u30b9\u30de\u30f3", "\u30c7\u30eb\u30d5\u30ea\u30f3\u30ac\u30fc"],
  "symbols": ["_", ",", ".", "!", "?", "-", "~", "\u2026", "A", "E", "I", "N", "O", "Q", "U", "a", "b", "d", "e", "f", "g", "h", "i", "j", "k", "m", "n", "o", "p", "r", "s", "t", "u", "v", "w", "y", "z", "\u0283", "\u02a7", "\u02a6", "\u2193", "\u2191", " "]
}