neuralsongstyle's Introduction

Neural Song Style

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

This is based on the implementation neural-style-audio 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

References

Audio texture synthesis and style transfe

neuralsongstyle's People

Contributors

Stargazers

Watchers

neuralsongstyle's Issues

Error in tensorflow

Python is 3.7, while tensorflow is 2.1.0
What happens:

Traceback (most recent call last):
File "/Users/aes1/Desktop/neuralaudiostyle.py", line 46, in
with g.as_default(), g.device('/cpu:0'), tf.Session() as sess:
AttributeError: module 'tensorflow' has no attribute 'Session'

error

python neuralaudiostyle.py --content dont.mp3  --style fade.mp3  --out out.wav
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcublas.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcudnn.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcufft.so locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:105] successfully opened CUDA library libcurand.so locally
('sampling rate :', 22050)
('sampling rate :', 22050)
audio style train

This remains like this by hours

Recommend Projects