midashenglm-7b-0804-fp32

user_prompt = "Caption the audio."  # You may try any other prompt

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": user_prompt},
            {
                "type": "audio",
                "path": "/path/to/example.wav",
                # or "url": "https://example.com/example.wav"
                # or "audio": np.random.randn(16000)
            },
        ],
    },
]