marian-nmt/marian
1
1
Fork 0
mirror of https://github.com/marian-nmt/marian.git synced 2025-01-08 17:41:07 +03:00
Code Issues Packages Projects Releases Wiki Activity
Fast Neural Machine Translation in C++
32 Commits 41 Branches 10 Tags 44 MiB
C++ 85.4%
Cuda 8.3%
CMake 3.3%
Python 1.8%
Batchfile 0.4%
Other 0.7%
30451239b8
Go to file
Kenneth Heafield 30451239b8 Shebang
2016-04-18 14:55:25 +00:00
scripts Shebang 2016-04-18 14:55:25 +00:00
src multi-gpu works with multiple threads but kenlm breaks 2016-04-16 20:13:03 +02:00
.gitignore Add python's pyc files to ignore 2016-04-15 16:27:48 +02:00
CMakeLists.txt User-specified kenlm path 2016-04-18 14:49:35 +00:00
LICENSE Initial commit 2016-04-14 11:27:41 +01:00
README Update README 2016-04-15 00:01:31 +01:00

README 

mkdir build
cd build
cmake ..
make -j

on Ubuntu 16.04, you need g++4.9 and cuda-7.5 and a boost version compiled with g++4.9

CUDA_BIN_PATH=/usr/local/cuda-7.5 BOOST_ROOT=/home/marcin/myboost cmake .. -DCMAKE_CXX_COMPILER=g++-4.9 -DCUDA_HOST_COMPILER=/usr/bin/g++-4.9

Vocabularies need to be converted to text with the scripts in the scripts folder.