/Chapter12

Chapter 12: End-to-end Speech Recognition

Primary LanguageJupyter Notebook

Deep Speech 2

This case study explores end-to-end ASR using the Deep Speech 2 architecture on PyTorch with the Common Voice dataset.

Running the Docker image with GPU

docker run -it --runtime=nvidia springernlp/chapter_12ds:latest

Requirements

The container will start a jupyter notebook. Follow the commands inside the Chapter 12 notebook.

Book Reference

More information can be found at: Deep Learning for NLP and Speech Recognition by Springer