Readme

Introduction

This is a simple application to separate audio resources, which is supported by the spleeter.

The project is used for Voice Recognition course taught by Prof.Ying Shen in Tongji University, Shanghai, China.

How to run

Prerequisite

python

anaconda

Configuration

Create conda environment

conda create Spleeter
activate Spleeter

Install dependencies

conda install -c conda-forge ffmpeg libsndfile

Install spleeter

pip install -i https://pypi.tuna.tsinghua.edu.cn/simple spleeter

Download FFmpegh and pre_trained models

https://zhuanlan.zhihu.com/p/645809914 This is the detailed installation and configuration steps.