faster-whisper

An OpenClaw skill that uses faster-whisper (a faster implementation of the Whisper transcription model) to transcribe audio, with additional features such as speaker diarization

10
安装命令
npx skhub add --skillset @theplasmak/faster-whisper

包含的技能

faster-whisper
Local speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.
00