Beast code in Giters

Kenneth Heafield's repositories

kenlm

KenLM: Faster and Smaller Language Model Queries

Language:C++NOASSERTION2461 69 366

preprocess

Corpus preprocessing

Language:C++NOASSERTION93 8 21

intgemm

int8_t and int16_t matrix multiply based on https://arxiv.org/abs/1705.01991

Language:C++NOASSERTION63 14 31

fasterText

Library for fast text representation and classification.

Language:HTMLMIT29 10

lazy

A lazy decoder for syntax

Language:C++NOASSERTION14 3 6

mtplz

Code for the paper Faster Phrase-Based Decoding by Refining Feature State

Language:C++NOASSERTION14 10 3

runforest

A python library that manages and runs experimental pipelines.

Language:PythonNOASSERTION4 30

elrc-scrape

Scrape ELRC-SHARE for corpora

Language:Python3 30

usage

Print resource usage of processes to stderr with LD_PRELOAD

Language:C++3 30

azurehacks

Hacks to control Azure instances

Language:Shell2 90

azure-batch-cli-extensions

Batch extension cli commands for Azure cli v2

Language:PythonNOASSERTION030

bitextor

Bitextor generates translation memories from multilingual websites.

Language:PythonGPL-3.0020

Bleualign

Machine-Translation-based sentence alignment tool for parallel text

Language:PythonGPL-2.0030

clean

A tool for downloading and cleaning parallel corpora

Language:ShellNOASSERTION010

CSrankings

A web app for ranking computer science departments according to their research output in selective venues.

Language:Python030

docs

Language:Makefile030

firefox-translations

Firefox Translations is a webextension that enables client side translations for web browsers.

Language:JavaScriptMPL-2.0010

firefox-translations-training

Training pipelines for Firefox Translations neural machine translation models

Language:PythonMPL-2.0010

incubator-joshua

Mirror of Apache Joshua (Incubating)

Language:JavaApache-2.0030

marian-dev

Fast Neural Machine Translation in C++ - development repository

Language:C++NOASSERTION010

masakhane-community

All our community docs! Start here! Lets put Africa on the NLP Map

MIT010

mtdata

A tool that locates, downloads, and extracts machine translation corpora. `pip install --ignore-installed mtdata`

Language:PythonApache-2.0010

OpenNMT

Open-Source Neural Machine Translation in Torch

Language:LuaMIT030

pcqueue

Simple pcqueue testing

Language:C++020

pyfasthash

Python Non-cryptographic Hash Library

Language:CApache-2.0010

SimpleGEN

Language:PythonMIT010

ssplit-cpp

Approximate reimplementation of the sentence splitter from the Moses toolkit.

Language:Emacs LispNOASSERTION020

tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.

Language:PythonApache-2.0030

translateLocally

Fast and secure translation on your local machine, powered by marian and Bergamot.

Language:C++MIT010

wmt17-website

Website for WMT17 - Second Conference in Machine Translation

Language:HTML030