SpecAugment is a SOTA-achieving data augmentation approach on speech recognition. The paper's authors did not publish code that I could find and their implementation was in TensorFlow.

1. run install.sh (I recommend to use a unique conda env for the project)
2. Check out SparseImageWarp.ipynb (a Jupyter notebook) for the functions.

1. Time Warp (Coming Soon) This augmentation relies on a lot of functionality not yet in Pytorch, so I have to write it from scratch. I am working on it.

2. Time Mask (DONE!)

3. Frequency Mask (DONE!)

Let's be friends! @zachcaceres zach.dev