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-only decoder implementation for easy deployment.
• Extensions to allow other sequence generation tasks such as summarization and image captioning.

OpenNMT only requires a vanilla torch/cutorch install. It uses nn, nngraph, and cunn. Alternatively there is a (CUDA) Docker container.

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

See the guide for more details.

• Options and Features
• Documentation
• Example Models
• Live Demo
• Bibliography