{
  "model_type": "zipformer",
  "feature_dim": 80,
  "output_downsampling_factor": 2,
  "num_encoder_layers": [
    2,
    2,
    4,
    5,
    4,
    2
  ],
  "downsampling_factor": [
    1,
    2,
    4,
    8,
    4,
    2
  ],
  "encoder_dim": [
    192,
    256,
    512,
    768,
    512,
    256
  ],
  "feedforward_dim": [
    576,
    768,
    1536,
    2304,
    1536,
    768
  ],
  "warmup_batches": 4000.0,
  "dropout": null,
  "num_heads": [
    4,
    4,
    4,
    8,
    4,
    4
  ],
  "query_head_dim": [
    32
  ],
  "value_head_dim": [
    12
  ],
  "pos_head_dim": [
    4
  ],
  "pos_dim": 48,
  "encoder_unmasked_dim": [
    192,
    192,
    256,
    256,
    256,
    192
  ],
  "cnn_module_kernel": [
    31,
    31,
    15,
    15,
    15,
    31
  ],
  "causal": false,
  "chunk_size": [
    16,
    32,
    64,
    -1
  ],
  "left_context_frames": [
    64,
    128,
    256,
    -1
  ]
}