https://github.com/seriouslysean/transcript-precombobulator
A tool to preprocess audio files for transcription by removing silence and preparing them for whisper.cpp
https://github.com/seriouslysean/transcript-precombobulator
audio-processing python transcription vad whisper
Last synced: 6 months ago
JSON representation
A tool to preprocess audio files for transcription by removing silence and preparing them for whisper.cpp
- Host: GitHub
- URL: https://github.com/seriouslysean/transcript-precombobulator
- Owner: seriouslysean
- Created: 2025-03-26T18:15:52.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2025-03-26T22:28:00.000Z (6 months ago)
- Last Synced: 2025-03-26T23:25:58.546Z (6 months ago)
- Topics: audio-processing, python, transcription, vad, whisper
- Language: Python
- Homepage:
- Size: 19.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: docs/README.md
Awesome Lists containing this project
README
# Transcript Precombobulator
Pre-processes audio files for better Whisper transcription by trimming silence and normalizing audio.
## Setup
```bash
brew install pyenv
git clone --recurse-submodules git@github.com:seriouslysean/transcript-precombobulator.git
cd transcript-precombobulator
make setup
# Always use make commands to ensure proper environment
make test # Test VAD on sample file
make run # Process all files
```