/beer

Bayesian spEEch Recognizer

Primary LanguagePythonMIT LicenseMIT

BEER: the Bayesian Speech Recognizer

Beer is a toolkit that provide Bayesian machine learning tools for speech technologies.

Beer is currently under construction and many things are subject to change !

Requirements

Beer is built upon the pytorch library. Beside, it also requires numpy and scipy. Finally, the examples use bokeh for visualization.

Installation

In a terminal type.

  $ python setup.py install

This will install beer and eventually numpy and sicpy if there are not install yet. Note that it will not automatically install pytorch. Please refer to the pytorch documentation to install it.

Usage

Have a look to our examples to get started with beer.