This module uses WhisperLive (https://github.com/collabora/WhisperLive) package to achieve a nearly real-time transcription module including VAD (Voice Activity Detection). Modifications are made on the WhisperLive source code to fit this project.
pip install requirements/server.txt
(if running server locally)pip install requirements/client.txt
docker build . -t whisper-live -f docker/Dockerfile.gpu
docker run -it --gpus all -p 9090:9090 whisper-live:latest
docker build . -t whisper-live -f docker/Dockerfile.cpu
docker run -it -p 9090:9090 whisper-live:latest
python run_server.py
python run_client.py