torch>=1.9.1
mediapipe>=0.8.8.1
opencv-contrib-python>=4.5.4.58
transformers>=4.4.0
opensmile>=2.2.0
librosa>=0.8.1
ffmpeg-python>=0.2.0
numpy>=1.20.3
pandas>=1.2.5
tqdm>=4.62.2
gdown>=4.4.0
scenedetect>=0.5.6.1
scipy>=1.7.3
python_speech_features>=0.6
