segmenter

A segmenter of speech audios. In comes a raw audio, out comes boundaries between speech and silence.

Usage

Via docker

docker build . -t segmenter
docker run -it --rm -v <INPUT_DATA>:/data:ro -v <OUTPUT_DATA>:/out segmenter /out /data

(recommended) Via python's virtual environment

1. Make sure pipenv is installed:

pip install pipenv

2. Clone this repository:

git clone https://github.com/SPIRA-COVID19/segmenter.git
cd segmenter/
pipenv sync

3. Run main:

pipenv run python main.py --help