Vocal remover using python
In this video tutorial, you will learn how to remove vocals from any music using Python. We will be using a GitHub repository and Anaconda to execute the application. However, it’s important to note that you should only remove vocals if you own the copyright of the music.
To get started, create a Python environment using Anaconda. Please install Python version 3.9. Download all the files from the GitHub repository and navigate to its folder to install the required dependencies.
We have noticed that the latest version of numpy didn’t work, so please install the lower version of numpy (1.23.0) as it worked for us. Likewise, install torch by running the following code as provided.
After completing all the steps, you should be able to remove vocals from any music. Try it out and let us know! Thank you very much.
1. Download and Install anaconda (https://www.anaconda.com/)
2. Open anaconda CMD
Installing python 3.9
1. conda create -n vocalremover python=3.9 (Creates an environment name vocalremover with python 3.9)
2. conda activate vocalremover (activates vocalremover (base) in front will change to vocalremover)
3. Navigate to the vocal-remover Python folder (download it from Github)
4. pip install -r requirements.txt (run this)
5. pip uninstall numpy
6. Install Lower Version of numpy
pip install numpy==1.23.0
7. Install torch
pip install torch==1.8.1+cu111 torchvision==0.9.1+cu111 torchaudio===0.8.1 -f https://download.pytorch.org/whl/torch_stable.html
8. Run application – remove vocals from Music
python inference.py –input “C:\Users….” –output_dir “C:\Users…..”