There seems to be a bug in the function upload_video() in the class Chat in file video_llama/conversation/conversation_video.py. On the 255 line of conversation_video.py, you directly pass the video_path to the function load_and_transform_audio_data(), which does not support video format. This would cause an exception in load_and_transform_audio_data(), resulting in skipping the audio loading while printing the information no audio is found.