This project transcribes video files and performs speaker diarization to generate a formatted transcript.
- Python 3.10: This project requires Python 3.10.
- Poetry: A Python dependency manager.
- Hugging Face Token: You need an access token to download models. Ensure you accept the model terms & conditions on huggingface.co.
- Input Video: A file named
video.mp4in the project root.
- Let poetry know that it should expect a virtual environment within the project directory
poetry config virtualenvs.in-project true- Create a virtual env with name
.venvas poetry tries to find that name by default.
python3.10 -m venv .venv- Activate the environment
source .venv/bin/activate- Install packages
poetry install- You should now be able to run the main.py file
python video_transcriber.pyRun the main script to process video.mp4 and generate the transcript:
python video_transcriber.py