image_audio/processing_metadata.json

{
  "source": "sglang",
  "model_id": "hf-internal-testing/tiny-inkling",
  "image_url": "http://images.cocodataset.org/val2017/000000039769.jpg",
  "audio_url": "https://huggingface.co/datasets/adarshxs/voxcpm2-native-generated-audio-user-ref/resolve/main/zs_medium.wav",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Describe the image and tell me what is said in the clip."
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "http://images.cocodataset.org/val2017/000000039769.jpg"
          }
        },
        {
          "type": "audio_url",
          "audio_url": {
            "url": "https://huggingface.co/datasets/adarshxs/voxcpm2-native-generated-audio-user-ref/resolve/main/zs_medium.wav"
          }
        }
      ]
    }
  ],
  "input_ids_len": 376,
  "num_image_tokens": 204,
  "num_audio_tokens": 148,
  "dmel_shape": [
    148,
    80
  ]
}