diff options
| author | jules@lens <julescarbon@gmail.com> | 2018-06-16 11:53:41 +0200 |
|---|---|---|
| committer | jules@lens <julescarbon@gmail.com> | 2018-06-16 11:53:41 +0200 |
| commit | 4c7ec7996256844a90b2187a3fea40a7e037b161 (patch) | |
| tree | 9b029688190e5d2d644e4d8612749df92c00bf8d /README.md | |
| parent | 410afb65bc350242d5ba248fb6a082db4d14e23b (diff) | |
needed to install LAME!
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 4 |
1 files changed, 4 insertions, 0 deletions
@@ -10,6 +10,10 @@ It's based on the reference implementation in Theano: https://github.com/soroush This code requires Python 3.5+ and PyTorch 0.1.12+. Installation instructions for PyTorch are available on their website: http://pytorch.org/. You can install the rest of the dependencies by running `pip install -r requirements.txt`. +``` +sudo apt install lame ffmpeg sox +``` + ## Datasets We provide a script for creating datasets from YouTube single-video mixes. It downloads a mix, converts it to wav and splits it into equal-length chunks. To run it you need youtube-dl (a recent version; the latest version from pip should be okay) and ffmpeg. To create an example dataset - 4 hours of piano music split into 8 second chunks, run: |