marian-nmt/marian
1
1
Fork 0
mirror of https://github.com/marian-nmt/marian.git synced 2024-12-11 09:54:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Marcin Junczys-Dowmunt 2016-05-01 10:37:35 +01:00
parent e6cb99c48c
commit 2f363e397e
1 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@ -7,16 +7,24 @@ A C++ decoder for Neural Machine Translation (NMT) models trained with Theano-ba
* CMake 3.5.1 (due to CUDA related bugs in earlier versions)
* Boost 1.5
* CUDA 7.5
* KenLM (https://github.com/kpu/kenlm, current master)
* yaml-cpp 0.5 (https://github.com/jbeder/yaml-cpp.git)
## Optional
* KenLM for n-gram language models (https://github.com/kpu/kenlm, current master)
## Compilation
The project is a standard Cmake out-of-source build:
mkdir build
cd build
cmake .. -DKENLM=path/to/kenlm
cmake ..
make -j
Or with KenLM support:
cmake .. -DKENLM=path/to/kenlm
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=/path/to/custom/boost cmake .. \