agentskillexchange Spleeter AI Audio Source Separation by Deezer
Spleeter is Deezer's open-source audio source separation library with pretrained models. It can split audio into 2, 4, or 5 stems (vocals, drums, bass, piano, accompaniment) and runs 100x faster than real-time on GPU, making it ideal for music production, remix, and audio analysis workflows.
Installation
Use the upstream install or setup path that matches your environment:
- conda install -c conda-forge ffmpeg libsndfile
- pip install spleeter
- git clone https://github.com/Deezer/spleeter && cd spleeter
- pip install poetry
Requirements and caveats from upstream:
- [![PyPI version]...
- written in Python and uses Tensorflow. It makes it easy
- as well as directly in your own development pipeline as a Python library. It can be installed with [pip](https://github.com/deezer/spleeter/wiki/1....
Basic usage or getting-started notes:
2 stems and 4 stems models have high performances on the musdb dataset. Spleeter is also very fast...
We designed Spleeter so you can use it straight from command line
Want to try it out but don't want to install anything ? We have set up a Google Colab.
Extracted from upstream docs: https://raw.githubusercontent.com/deezer/spleeter/HEAD/README.md