{
  "architectures": [
    "FunASRForConditionalGeneration"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "max_position_embeddings": 40960,
  "max_window_layers": 28,
  "model_type": "qwen3",
  "num_attention_heads": 16,
  "num_hidden_layers": 28,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936,
  "max_source_positions": 1500,
  "decoder_start_token_id": 99999,
  "audio_encoder": "SenseVoiceEncoderSmall",
  "audio_encoder_conf": {
      "output_size": 512,
      "attention_heads": 4,
      "linear_units": 2048,
      "num_blocks": 50,
      "tp_blocks": 20,
      "dropout_rate": 0.1,
      "positional_dropout_rate": 0.1,
      "attention_dropout_rate": 0.1,
      "input_layer": "pe",
      "pos_enc_class": "SinusoidalPositionEncoder",
      "normalize_before": true,
      "kernel_size": 11,
      "sanm_shfit": 0,
      "selfattention_layer_type": "sanm",
      "freeze": true,
      "freeze_layer_num": -1,
      "feat_permute": true
  }
}