Fast Neural Machine Translation in C++
Go to file
2017-07-20 16:00:19 +02:00
cmake Switch to manual project versioning 2017-07-13 13:02:43 +01:00
contrib Remove old script 2017-07-13 13:04:31 +01:00
doc Added more references 2016-10-06 10:25:53 -05:00
scripts make hard-attention models work 2017-07-10 18:14:43 +00:00
src Default arguments ruin everything 2017-07-19 15:33:49 -07:00
.clang-format Add .clang-format file 2017-06-05 12:18:19 +02:00
.gitignore Add project versioning 2017-07-04 14:06:26 +01:00
CMakeLists.txt Switch to manual project versioning 2017-07-13 13:02:43 +01:00
Doxyfile.in Exclude 3rd party code from generated docs 2016-10-03 12:31:54 -05:00
LICENSE.md Update LICENSE.md 2017-02-27 01:16:42 +00:00
README.md Update README.md 2017-07-18 10:47:32 +02:00
VERSION Switch to manual project versioning 2017-07-13 13:02:43 +01:00

Marian

Join the chat at https://gitter.im/amunmt/marian Build Status

Google group for commit messages: https://groups.google.com/forum/#!forum/mariannmt

marian-train is a C++ GPU-specific parallel automatic differentiation library with operator overloading. It is the training framework used in the Marian toolkit.

Named in honour of Marian Rejewski, a Polish mathematician and cryptologist.

Website

More information on https://marian-nmt.github.io

Acknowledgements

The development of Marian received funding from the European Union's Horizon 2020 Research and Innovation Programme under grant agreements 688139 (SUMMA; 2016-2019), 645487 (Modern MT; 2015-2017) and 644333 (TraMOOC; 2015-2017), the Amazon Academic Research Awards program, and the World Intellectual Property Organization.

This software contains source code provided by NVIDIA Corporation.