Fills censored English words in YouTube captions using surrounding caption context and a local Whisper audio inference model. Fully local and open-source.
Options
- Off — disables caption filling.
- Rules only — uses only caption context. Minimal CPU load, high precision, but low coverage.
- Rules first (Recommended) — uses context for most fills and Whisper for the remaining slots. High precision and coverage with moderate CPU usage.
- Whisper first — uses Whisper on every slot, with rules filling any slots the model misses. Maximum precision and coverage with high CPU usage.
- Whisper only — uses only Whisper. Maximum precision and high coverage.
Watch videos on mute or in loud areas. Requested by the deaf community.