{ "adaptor_downsample_rate": 1, "adaptor_dropout": 0.0, "adaptor_intermediate_size": 2048, "adaptor_num_attention_heads": 8, "adaptor_num_hidden_layers": 2, "architectures": [ "FunAsrNanoForConditionalGeneration" ], "audio_encoder_config": { "attention_dropout": 0.0, "dropout": 0.1, "encoder_layers": 50, "initializer_range": 0.02, "input_size": 560, "intermediate_size": 2048, "kernel_size": 11, "model_type": "fun_asr_nano_encoder", "num_attention_heads": 4, "output_dim": 512, "sanm_shift": 0, "tp_blocks": 20 }, "audio_token_index": 151646, "dtype": "bfloat16", "initializer_range": 0.02, "model_type": "fun_asr_nano", "text_config": { "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 3072, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 40960, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "pad_token_id": null, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 1000000, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": true, "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "tie_word_embeddings": true, "transformers_version": "5.13.0.dev0" }