Introduction

This repo is my notebook to learn about end-to-end speech recognition. There are many projects that work on end-to-end speech recognition. But they are either hard to install or hard to reproduce, i.e. not simple enough for a beginner. This project is intended for beginners who know basics about speech recognition and desire a handy 101 tutorial on end-to-end SR.

If you have any question, welcome to file an issue!

List (to be expanded)

• CTC: an interactive CTC trainer using YesNo data.

Credits

This project is inspired by:

• Deep Learning with PyTorch
• rnn-transducer