Fork me on GitHub

MarianNMT

Fast Neural Machine Translation in C++

  1. Quick start
  2. Features & Benchmarks
  3. Documentation
  4. Examples
  5. FAQ
  6. Publications
  7. Blog

Marian is an efficient, free Neural Machine Translation framework written in pure C++ with minimal dependencies. It is mainly being developed by the Microsoft Translator team. Many academic (most notably the University of Edinburgh and in the past the Adam Mickiewicz University in Poznań) and commercial contributors help with its development.

It is currently the engine behind the Microsoft Translator Neural Machine Translation services and being deployed by many companies, organizations and research projects (see below for an incomplete list).

Main features:

  • Efficient pure C++ implementation
  • Fast multi-GPU training and GPU/CPU translation
  • State-of-the-art NMT architectures: deep RNN and Transformer
  • Permissive open source license (MIT)
  • more details...

Download from GitHub Follow Marian on Twitter

Quick Start

Minimal examples for compilation, training, translation

Features & Benchmarks

Feature list, translation and training benchmarks

Documentation

Extended description of command line options

Examples

End-to-end examples how to train and translate with our toolkit

FAQ

Look for answers or post your own question

Developer API

Developer documentation and library API

Companies and organizations using Marian

Microsoft

All other trademarks are the property of their respective owners.

AYLIEN
Air Force Research Laboratory
Bergamot
CPSL
EBay
European Commission
FISKMÖ
GoURMET
HimL
Intel
International Maritime Organization
Lingea
Lingo24
Lingoclinix
Microsoft Translator
Opus-MT
ParaCrawl
Qordoba
Rakuten
SUMMA
Sapling
Skrivanek
Tilde
Unbabel
Wikimedia Foundation
World Intellectual Property Organization
World Trade Organization

If you would like to have your logo and link added to this list please add a comment with pointers which logo to use to this thread.

Acknowledgements

Marian is mainly being developed by the Microsoft Translator team and many academic and commercial contributors. The development of Marian received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreements No 688139 (SUMMA; 2016-2019), 645487 (Modern MT; 2015-2017), 644333 (TraMOOC; 2015-2017), 644402 (HimL; 2015-2017), 825303 (Bergamot; 2019-2021), 825627 (ELG; 2019-2021), the European Union's Connecting Europe Facility project 2019-EU-IA-0045 (User-focused Marian; 2020-2022), the Amazon Academic Research Awards program, the World Intellectual Property Organization, the eBay Research and University Partnership for Technology program, a collaboration with Intel, and is based upon work supported in part by the Office of the Director of National Intelligence (ODNI), Intelligence Advanced Research Projects Activity (IARPA), via contract #FA8650-17-C-9117. Intel and the Intel logo are trademarks of Intel Corporation in the U.S. and other countries.