{
  "transformer_encoder_layers_cfg": {
    "d_model": 768,
    "nhead": 12,
    "batch_first": true,
    "norm_first": false,
    "bias": true,
    "dim_feedforward": 3072,
    "dropout": 0.0,
    "activation": "GELU(approximate='none')",
    "layer_norm_eps": 1e-06
  },
  "transformer_encoder_cfg": {
    "num_layers": 12,
    "enable_nested_tensor": false,
    "mask_check": true
  },
  "lr": 0.0004,
  "adam_betas": [
    0.9,
    0.98
  ],
  "adam_eps": 1e-06,
  "adam_weight_decay": 0.01,
  "ema_decay": 0.999,
  "ema_end_decay": 0.99999,
  "ema_anneal_end_step": 100000,
  "warmup_steps": 100000,
  "average_top_k_layers": 8,
  "resample_sr": 16000,
  "original_sr": 16000,
  "use_gradient_checkpointing": false,
  "compile_modules": false,
  "size": "base",
  "clean_audio_ratio": 0.0
}