{
  "encoder_dim": 620,
  "decoder_dim": 512,
  "depth": 10,
  "nheads": 8,
  "head_dim": 64,
  "vocab_size": 32768,
  "bos_id": 1,
  "eos_id": 2,
  "frame_len": 80,
  "total_lookahead": 16,
  "d_model_frontend": 620,
  "c1": 1240,
  "c2": 620,
  "frontend_state_shapes": {
    "sample_buffer": [
      1,
      79
    ],
    "sample_len": [
      1
    ],
    "conv1_buffer": [
      1,
      620,
      4
    ],
    "conv2_buffer": [
      1,
      1240,
      4
    ],
    "frame_count": [
      1
    ]
  }
}