knownasnaffy Cleanup Review
python scripts/_cache_clear.py is an optional cleanup helper for the Whisper Transcribe skill. It may recursively remove /tmp/skill_build/*, /tmp/skill_build/.cache. Show the exact paths first, explain whether they are skill-private temporary paths or user state, and run the cleanup only after the user confirms.
Whisper Transcribe
Transcribe audio with scripts/transcribe.sh:
# Basic (auto-detect language, base model)
scripts/transcribe.sh recording.mp3
# German, small model, SRT subtitles
scripts/transcribe.sh --model small --language de --format srt lecture.wav
# Batch process, all formats
scripts/transcribe.sh --format all --output-dir ./transcripts/ *.mp3
# Word-level timestamps
scripts/transcribe.sh --timestamps interview.m4a
Models
| Model | RAM | Speed | Accuracy | Best for |
|---|---|---|---|---|
| tiny | ~1GB | ⚡⚡⚡ | ★★ | Quick drafts, known language |
| base | ~1GB | ⚡⚡ | ★★★ | General use (default) |
| small | ~2GB | ⚡ | ★★★★ | Good accuracy |
| medium | ~5GB | 🐢 | ★★★★★ | High accuracy |
| large | ~10GB | 🐌 | ★★★★★ | Best accuracy (slow on Pi) |
Output Formats
- txt — Plain text transcript
- srt — SubRip subtitles (for video)
- vtt — WebVTT subtitles
- json — Detailed JSON with timestamps and confidence
- all — Generate all formats at once
Requirements
whisperCLI (pip install openai-whisper)ffmpeg(for audio decoding)- First run downloads the model (~150MB for base)