This project allows you to download audio from Vimeo videos, transcribe it using OpenAI’s Whisper model, and save the results as text files — all in an automated workflow.
- Download audio from Vimeo using
yt-dlp - Transcribe audio using OpenAI's Whisper model
- Save transcriptions to
.txtfiles - Clean up audio files after transcription
- Simple and extensible project structure
Before running the script, make sure you have the following installed:
- Python 3.7 or higher
- yt-dlp
- OpenAI Whisper
- ffmpeg
- tqdm
pip install yt-dlp tqdm
pip install git+https://github.com/openai/whisper.git