Kenneth Heafield's repositories
preprocess
Corpus preprocessing
fasterText
Library for fast text representation and classification.
elrc-scrape
Scrape ELRC-SHARE for corpora
azurehacks
Hacks to control Azure instances
azure-batch-cli-extensions
Batch extension cli commands for Azure cli v2
CSrankings
A web app for ranking computer science departments according to their research output in selective venues.
firefox-translations
Firefox Translations is a webextension that enables client side translations for web browsers.
firefox-translations-training
Training pipelines for Firefox Translations neural machine translation models
incubator-joshua
Mirror of Apache Joshua (Incubating)
marian-dev
Fast Neural Machine Translation in C++ - development repository
masakhane-community
All our community docs! Start here! Lets put Africa on the NLP Map
pyfasthash
Python Non-cryptographic Hash Library
ssplit-cpp
Approximate reimplementation of the sentence splitter from the Moses toolkit.
tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
translateLocally
Fast and secure translation on your local machine, powered by marian and Bergamot.
wmt17-website
Website for WMT17 - Second Conference in Machine Translation