Using TensorFlow Autoencoders with Music – Good Audience

Once I finished converting all of the MP3 files into WAV files, I had to figure out how to load in the WAV data. Putting the data into a format that a neural network can work with, to me, was one of the hardest parts. This project took a lot of trial and error to get working correctly, but was pretty fun to figure out. To help me process the WAV files, I used TensorFlow's audio_ops library. I opted to use audio_ops to decode the WAV files into an array of samples that could then be processed and batched.