configs/s2.json

{
  "train": {
    "log_interval": 100,
    "eval_interval": 500,
    "seed": 1234,
    "epochs": 100,
    "learning_rate": 0.0001,
    "betas": [
      0.8,
      0.99
    ],
    "eps": 1e-09,
    "batch_size": 32,
    "fp16_run": true,
    "lr_decay": 0.999875,
    "segment_size": 20480,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0,
    "text_low_lr_rate": 0.4
  },
  "data": {
    "max_wav_value": 32768.0,
    "sampling_rate": 32000,
    "filter_length": 2048,
    "hop_length": 640,
    "win_length": 2048,
    "n_mel_channels": 128,
    "mel_fmin": 0.0,
    "mel_fmax": null,
    "add_blank": true,
    "n_speakers": 300,
    "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": [
      10,
      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,
    "semantic_frame_rate": "25hz",
    "freeze_quantizer": true
  },
  "s2_ckpt_dir": "logs/s2/big2k1",
  "content_module": "cnhubert"
}