Transcribe meeting recordings locally (Whisper / faster-whisper)

Symptoms

• Meetings are confidential, so cloud notetakers are out
• You have a backlog of recordings to transcribe

Common causes

• Cloud tools need audio uploads
• The original Whisper is slow on CPU

How to fix

1. Install Python and pip install faster-whisper (officially up to 4× faster than openai/whisper at the same accuracy, with less memory)
2. Use the GPU if you have NVIDIA; otherwise run int8 on CPU
3. Try small / medium models for speed, then large models for accuracy
4. Use WhisperX when you need speaker diarisation
5. Summarise the transcript with a local model (e.g. Ollama) into decisions / actions / open questions and proof names and numbers

Notes

• Tell participants before recording
• Models get proper nouns wrong; give a glossary in the prompt