SpecAugment

A Pytorch Implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

Medium Article

SpecAugment is a state of the art data augmentation approach for speech recognition.

The original implementation is from DemisEom and bobchennan.

To run this SpecAugment

  1. Install SpecAugment library by

    pip install SpecAugment

  2. Run the file, spec_augment_test_pytorch.py.