{
  "format_version": 1,
  "type": "speaker",
  "model": {
    "extractor_mode": "layer_norm",
    "encoder_layers": 24,
    "encoder_embed_dim": 1024,
    "encoder_ffn_embed_dim": 4096,
    "encoder_attention_heads": 16,
    "activation_fn": "gelu",
    "dropout": 0.0,
    "attention_dropout": 0.0,
    "activation_dropout": 0.0,
    "encoder_layerdrop": 0.0,
    "dropout_input": 0.0,
    "dropout_features": 0.0,
    "layer_norm_first": true,
    "conv_feature_layers": [
      [
        512,
        10,
        5
      ],
      [
        512,
        3,
        2
      ],
      [
        512,
        3,
        2
      ],
      [
        512,
        3,
        2
      ],
      [
        512,
        3,
        2
      ],
      [
        512,
        2,
        2
      ],
      [
        512,
        2,
        2
      ]
    ],
    "conv_bias": false,
    "feature_grad_mult": 1.0,
    "mask_length": 10,
    "mask_prob": 0.8,
    "mask_selection": "static",
    "mask_other": 0.0,
    "no_mask_overlap": false,
    "mask_min_space": 1,
    "mask_channel_length": 10,
    "mask_channel_prob": 0.0,
    "mask_channel_selection": "static",
    "mask_channel_other": 0.0,
    "no_mask_channel_overlap": false,
    "mask_channel_min_space": 1,
    "conv_pos": 128,
    "conv_pos_groups": 16,
    "relative_position_embedding": true,
    "num_buckets": 320,
    "max_distance": 800,
    "gru_rel_pos": true,
    "normalize": true
  }
}