configs/configs_jp_extra.json

{
  "train": {
    "log_interval": 200,
    "eval_interval": 1000,
    "seed": 42,
    "epochs": 1000,
    "learning_rate": 0.0001,
    "betas": [0.8, 0.99],
    "eps": 1e-9,
    "batch_size": 2,
    "bf16_run": false,
    "fp16_run": false,
    "lr_decay": 0.99996,
    "segment_size": 16384,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0,
    "c_commit": 100,
    "skip_optimizer": false,
    "freeze_ZH_bert": false,
    "freeze_JP_bert": false,
    "freeze_EN_bert": false,
    "freeze_emo": false,
    "freeze_style": false,
    "freeze_decoder": false
  },
  "data": {
    "use_jp_extra": true,
    "training_files": "filelists/train.list",
    "validation_files": "filelists/val.list",
    "max_wav_value": 32768.0,
    "sampling_rate": 44100,
    "filter_length": 2048,
    "hop_length": 512,
    "win_length": 2048,
    "n_mel_channels": 128,
    "mel_fmin": 0.0,
    "mel_fmax": null,
    "add_blank": true,
    "n_speakers": 512,
    "cleaned_text": true
  },
  "model": {
    "use_spk_conditioned_encoder": true,
    "use_noise_scaled_mas": true,
    "use_mel_posterior_encoder": false,
    "use_duration_discriminator": false,
    "use_wavlm_discriminator": true,
    "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, 2],
    "upsample_initial_channel": 512,
    "upsample_kernel_sizes": [16, 16, 8, 2, 2],
    "n_layers_q": 3,
    "use_spectral_norm": false,
    "gin_channels": 512,
    "slm": {
      "model": "./slm/wavlm-base-plus",
      "sr": 16000,
      "hidden": 768,
      "nlayers": 13,
      "initial_channel": 64
    }
  },
  "version": "2.3-JP-Extra"
}