This project is about MelGAN, proposed in this paper.
Quick start
If you want run script and don't care you can run this commands in your terminal:
gitclonehttps://github.com/PUSSYMIPT/MelGAN.git&&cdMelGANpipinstall-rrequirements/requirements.txtsudoapt-getinstalllibsndfile1-y# not necessary but sometimes requiredbashbin/download_lj_speech.shexport PYTHONPATH=$PYTHONPATH:. # not necessary but sometimes requiredbashbin/download_lj_speach.shpythonscripts/preprocess.py-ddata/LJSpeech-1.1/wavscatalyst-dlrun-Cconfigs/LJ_config.yml--verbose
Run experiment
First of all we need to install all required dependencies
$ pip install -r requirements/requirements.txt
Sometimes if librosa wasn't install we also need to install some other additional library
$sudoapt-getinstalllibsndfile1-y
Also we need to download and preprocess dataset. For example LJ1.1.
bashbin/download_lj_speech.shexport PYTHONPATH=$PYTHONPATH:. # not necessary but sometimes requiredbashbin/download_lj_speach.shpythonscripts/preprocess.py-ddata/LJSpeech-1.1/wavs
Config API
The most product-ready and kinda professional way to run script in catalyst is to run it via config API. You need to write your config.yml file and download your dataset. Then just run