{ "model_type": "toy_qwen3_asr", "model_size": "toy-0b", "support_languages": ["English", "Chinese"], "thinker_config": { "model_type": "toy_qwen3_asr", "audio_token_id": 151646, "audio_config": { "num_mel_bins": 128, "encoder_layers": 2, "encoder_attention_heads": 4, "encoder_ffn_dim": 256, "d_model": 128, "n_window": 100, "n_window_infer": 100, "conv_chunksize": 100, "downsample_hidden_size": 128, "output_dim": 128, "activation_function": "gelu" }, "text_config": { "vocab_size": 128, "hidden_size": 128, "intermediate_size": 256, "num_hidden_layers": 2, "num_attention_heads": 4, "num_key_value_heads": 2, "max_position_embeddings": 512 } } }