https://github.com/rupeshs/neuralsongstyle

Audio style transfer AI
https://github.com/rupeshs/neuralsongstyle

python style styletransfer tensorflow

Last synced: about 1 year ago
JSON representation

Audio style transfer AI

• Host: GitHub
• URL: https://github.com/rupeshs/neuralsongstyle
• Owner: rupeshs
• Created: 2016-12-18T01:58:13.000Z (over 9 years ago)
• Default Branch: master
• Last Pushed: 2024-10-20T01:16:05.000Z (over 1 year ago)
• Last Synced: 2025-03-28T01:06:47.014Z (about 1 year ago)
• Topics: python, style, styletransfer, tensorflow
• Language: Python
• Homepage:
• Size: 1.69 MB
• Stars: 152
• Watchers: 10
• Forks: 26
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml

Awesome Lists containing this project

README

          
# Neural Song Style

Transferring the style from one song onto another using artificial intelligence.

This is based on the implementation [neural-style-audio](https://github.com/DmitryUlyanov/neural-style-audio-tf) by Dmitry and Vadim.

### Options

 - --content ,Content audio path

 - --style, Style audio path

 - --out,   Styled audio path

### Dependencies

- python (tested with python 2.7/3.5)

- tensorflow

- librosa

### Demo 

00:00-00:10 - Content - Alan Walker fade

00:10-00:20 - Style- Chain smokers -Don't Let Me Down

00:10-00:30 - Styled song

[Song style transfer AI test](https://www.youtube.com/watch?v=iUujo7i6P3w)

![Spectrum](https://raw.githubusercontent.com/rupeshs/neuralsongstyle/master/plots/spectrum.jpg "Spectrum")

### References

[Audio texture synthesis and style transfe](http://dmitryulyanov.github.io/audio-texture-synthesis-and-style-transfer/)