marian-nmt/marian
1
1
Fork 0
mirror of https://github.com/marian-nmt/marian.git synced 2024-11-27 10:33:14 +03:00
Code Issues Packages Projects Releases Wiki Activity
Fast Neural Machine Translation in C++
109 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%
7e76b61f88
Go to file
Marcin Junczys-Dowmunt 7e76b61f88 Towards YAML configurations
2016-04-28 20:00:43 +02:00
cmake Towards YAML configurations 2016-04-28 20:00:43 +02:00
scripts fixed tuning 2016-04-27 12:48:50 +02:00
src Towards YAML configurations 2016-04-28 20:00:43 +02:00
.gitignore Add python's pyc files to ignore 2016-04-15 16:27:48 +02:00
CMakeLists.txt Towards YAML configurations 2016-04-28 20:00:43 +02:00
LICENSE Initial commit 2016-04-14 11:27:41 +01:00
README.md Update README.md 2016-04-21 00:07:59 +01:00

README.md

amuNN

A C++ decoder for Neural Machine Translation (NMT) models trained with Theano-based scripts from DL4MT (https://github.com/nyu-dl/dl4mt-tutorial)

Requirements:

Compilation

The project is a standard Cmake out-of-source build:

mkdir build
cd build
cmake .. -DKENLM=path/to/kenlm
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=/path/to/custom/boost cmake .. \
-DCMAKE_CXX_COMPILER=g++-4.9 -DCUDA_HOST_COMPILER=/usr/bin/g++-4.9 -DKENLM=path/to/kenlm

Vocabularies (*.pkl extension) need to be converted to text with the scripts in the scripts folder.

python scripts/vocab2txt.py vocab.en.pkl > vocab.en