loretoparisi / Conditioned-Source-Separation-LaSAFT

A PyTorch implementation of the paper: "LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

lasaft-docker

This code is an adaption of ws-choi Conditioned-Source-Separation-LaSAFT to run over CPU in a Docker container.

Build docker

docker build -f Dockerfile -t lasaft .
docker run --rm -it -d -v `pwd`/src:/app -v /root:/root --name lasaft-test lasaft
docker exec -it lasaft-test bash

Run docker image

python Separation_wav.py -mix_scp /root/test.wav -yaml options/train/train.yml -model /root/best.pt -save_path ./checkpoint

Run Inference

python inference.py --url "youtube-url" --s 0 --e 10

python inference.py --a /path/to/audio.wav --s 0 --e 10

References

About

A PyTorch implementation of the paper: "LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation"

License:MIT License


Languages

Language:Jupyter Notebook 99.9%Language:Python 0.1%Language:Dockerfile 0.0%