Skip to content

noahvrz/speech_recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

Speech Recognition

Performs speech recognition on the LibriSpeech dataset. Uses an end-to-end model based of Baidu's Deep Speech 2. Implemented in Keras and TensorFlow.

Still very much a work in progress pending access to a strong GPU. These networks are really big and require huge amounts of computational power.

Written as my final project for an Oxford course in Deep Learning for Natural Language Processing.

About

Uses a series of convolutional and recurrent layers to learn to recognize speech.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published