Catalan Voice Recognition
-------------------------------------------------

This repository collects several scripts and other resources related
to developing voice recognition tools for the Catalan language.


LANGUAGE_MODEL
-----------------------------

This directory contains scripts to parse an XML dump of the Catalan
Wikipedia, extract all article sentences and generate statistics on
the n-grams found in them.


SIMPLE_RECOGNIZER
-----------------------------

This is a simple DTW speech recognizer, for things such as digits.
It's been tried as a fun project and shouldn't be taken seriously.