https://github.com/OpenNMT/OpenNMT

Open Source Neural Machine Translation in Torch (deprecated)
https://github.com/OpenNMT/OpenNMT

deep-learning lua machine-translation neural-machine-translation opennmt torch

Last synced: 3 months ago
JSON representation

Open Source Neural Machine Translation in Torch (deprecated)

• Host: GitHub
• URL: https://github.com/OpenNMT/OpenNMT
• Owner: OpenNMT
• License: mit
• Archived: true
• Created: 2016-10-24T16:09:20.000Z (about 8 years ago)
• Default Branch: master
• Last Pushed: 2020-02-19T16:08:46.000Z (almost 5 years ago)
• Last Synced: 2024-09-29T15:23:15.148Z (4 months ago)
• Topics: deep-learning, lua, machine-translation, neural-machine-translation, opennmt, torch
• Language: Lua
• Homepage: https://opennmt.net/
• Size: 25.8 MB
• Stars: 2,386
• Watchers: 151
• Forks: 467
• Open Issues: 46
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
**This project is considered obsolete as the Torch framework is no longer maintained. If you are starting a new project, please use an alternative in the OpenNMT family: [OpenNMT-tf](https://github.com/OpenNMT/OpenNMT-tf) (TensorFlow) or [OpenNMT-py](https://github.com/OpenNMT/OpenNMT-py) (PyTorch) depending on your requirements.**

[![Build Status](https://api.travis-ci.org/OpenNMT/OpenNMT.svg?branch=master)](https://travis-ci.org/OpenNMT/OpenNMT) [![codecov](https://codecov.io/gh/OpenNMT/OpenNMT/branch/master/graph/badge.svg)](https://codecov.io/gh/OpenNMT/OpenNMT)

# OpenNMT: Open-Source Neural Machine Translation

[OpenNMT](http://opennmt.net/) is a full-featured, open-source (MIT) neural machine translation system utilizing the [Torch](http://torch.ch) 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](https://github.com/OpenNMT/CTranslate) 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](http://torch.ch/docs/getting-started.html)

2. Install additional packages:

```bash

luarocks install tds

luarocks install bit32 # if using LuaJIT

```

For other installation methods including Docker, visit the [documentation](http://opennmt.net/OpenNMT/installation/).

## 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

```

2) Train the model.

```

th train.lua -data data/demo-train.t7 -save_model model

```

3) Translate sentences.

```

th translate.lua -model model_final.t7 -src data/src-test.txt -output pred.txt

```

For more details, visit the [documentation](http://opennmt.net/OpenNMT/).

## Citation

A [technical report](https://arxiv.org/abs/1701.02810) 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}

}

```

## Acknowledgments

Our implementation utilizes code from the following:

* [Andrej Karpathy's char-rnn repo](https://github.com/karpathy/char-rnn)

* [Wojciech Zaremba's lstm repo](https://github.com/wojzaremba/lstm)

* [Element rnn library](https://github.com/Element-Research/rnn)

## Additional resources

* [Documentation](http://opennmt.net/OpenNMT)

* [Forum](http://forum.opennmt.net)

* [Gitter channel](https://gitter.im/OpenNMT/openmt)