TensorFlow implementation for audio neural style.
Jupyter Notebook
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
inputs initial Dec 13, 2016
outputs initial Dec 13, 2016
README.md readme Dec 14, 2016
neural-style-audio-tf.ipynb update Dec 13, 2016

README.md

Audio Style Transfer

This is a TensorFlow reimplementation of Vadim's Lasagne code for style transfer algorithm for audio, which uses convolutions with random weights to represent audio features.

To listen to examples go to the blog post. Also check out Torch implementation.

So far it is CPU only, but if you are proficient in TensorFlow it should be easy to switch. Actually it runs fast on CPU.

Dependencies

pip install librosa
  • numpy and matplotlib

The easiest way to install python is to use Anaconda.

How to run

  • Open neural-style-audio-tf.ipynb in Jupyter.
  • In case you want to use your own audio files as inputs, first cut them to 10s length with:
ffmpeg -i yourfile.mp3 -ss 00:00:00 -t 10 yourfile_10s.mp3
  • Set CONTENT_FILENAME and STYLE_FILENAME in the third cell of Jupyter notebook to your input files.
  • Run all cells.

The most frequent problem is domination of either content or style in the output. To fight this problem, adjust ALPHA parameter. Larger ALPHA means more content in the output, and ALPHA=0 means no content, which reduces stylization to texture generation. Example output outputs/imperial_usa.wav, the result of mixing content of imperial march from star wars with style of U.S. National Anthem, was obtained with default value ALPHA=1e-2.

References