Skip to content

Open-Source Neural Machine Translation in Torch

License

Notifications You must be signed in to change notification settings

brokenpeace/OpenNMT

 
 

Repository files navigation

Build Status codecov

OpenNMT: Open-Source Neural Machine Translation

OpenNMT is a full-featured, open-source (MIT) neural machine translation system utilizing the Torch mathematical toolkit.

The system is designed to be simple to use and easy to extend, while maintaining efficiency and state-of-the-art translation accuracy. Features include:

  • Speed and memory optimizations for high-performance GPU training.
  • Simple general-purpose interface, only requires and source/target data files.
  • C++ implementation of the translator for easy deployment.
  • Extensions to allow other sequence generation tasks such as summarization and image captioning.

Installation

OpenNMT only requires a Torch installation with few dependencies.

  1. Install Torch
  2. Install additional packages:
luarocks install tds

For other installation methods including Docker, visit the documentation.

Quickstart

OpenNMT consists of three commands:

  1. Preprocess the data.
th preprocess.lua -train_src data/src-train.txt -train_tgt data/tgt-train.txt -valid_src data/src-val.txt -valid_tgt data/tgt-val.txt -save_data data/demo
  1. Train the model.
th train.lua -data data/demo-train.t7 -save_model model
  1. Translate sentences.
th translate.lua -model model_final.t7 -src data/src-test.txt -output pred.txt

For more details, visit the documentation.

Citation

A technical report on OpenNMT is available. If you use the system for academic work, please cite:

@ARTICLE{2017opennmt,
  author = {{Klein}, G. and {Kim}, Y. and {Deng}, Y. and {Senellart}, J. and {Rush}, A.~M.},
  title = "{OpenNMT: Open-Source Toolkit for Neural Machine Translation}",
  journal = {ArXiv e-prints},
  eprint = {1701.02810}
}

Additional resources

About

Open-Source Neural Machine Translation in Torch

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Lua 97.1%
  • Perl 1.4%
  • Python 1.1%
  • Shell 0.4%