Separation of Music and Voice

This application is based On Deep neural Networks and deployment from the Flask.

• separation of music and voice
• mixing two audios

New Features!

• Import a Audio file and watch it magically separate background music and voice
• Record your own voice

You can also:

• Import and save files from GitHub and reasearch paper.

Installation

Pytorch requires Pytorch.org to run.

Install the dependencies and devDependencies and start the server.

$ cd seaparation of music and voice
$ pip install pytorch
$ pip install flask
$ pip install pydub

For production environments...

$ creating virtual environment for flask [flask](https://code.visualstudio.com/docs/python/tutorial-flask)

Development

Want to contribute? Great!

Make a change in your file and instantaneously see your updates!

Open your favorite Terminal and run these commands.

First Tab:

$ clone https://github.com/navneet2104/Separating-music-and-voice-from-vocal-rap-songs-for-generating-engaging-visualizer.git

Second Tab:

$ cd voice

(optional) Third:

$ python app.py

Contributions

Navneet agarwal(https://github.com/navneet2104)

suryapal Singh(https://github.com/mespsar)

Vishal Shashikant Bhandari

Under the Guidance of : Dr. Sridhar Swaminathan

Blog by navneet agarwal:

https://medium.com/@navneet.agarwal.97521/separation-of-music-and-voice-using-deep-learning-ef322ba00d50

Youtube vide:

comming soon