{
  "architectures": [
    "SenseVoiceEncoder"
  ],
  "model_type": "sensevoice_encoder_portable",
  "auto_map": {
    "AutoConfig": "configuration_sensevoice_encoder.SenseVoiceEncoderConfig",
    "AutoModel": "modeling_sensevoice_encoder.SenseVoiceEncoder"
  },
  "input_size": 560,
  "output_size": 512,
  "attention_heads": 4,
  "linear_units": 2048,
  "num_blocks": 50,
  "tp_blocks": 20,
  "kernel_size": 11,
  "sanm_shfit": 0,
  "n_mels": 80,
  "lfr_m": 7,
  "lfr_n": 6,
  "frame_length": 25,
  "frame_shift": 10,
  "num_query_embeddings": 16,
  "language_id": 0,
  "textnorm_id": 15,
  "torch_dtype": "float32"
}