openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision

Whisper Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition. Whisper's performance varies widely depending on the import whisper model = whisper. The codebase is expected to be compatible with Python 3.7 or later and recent andrecent and recent PyTorch versions.