OpenNMT is an open source ecosystem for neural machine translation and neural sequence learning.

Started in December 2016 by theHarvard NLP group andSYSTRAN, the project has since been used inseveral research and industry applications. It is currently maintained bySYSTRAN andUbiqus.

OpenNMT provides implementations in 2 popular deep learning frameworks:

OpenNMT-py

User-friendly and multimodal, benefiting from PyTorch ease of use.

• Documentation
• Pretrained models

OpenNMT-tf

Modular and stable, powered by the TensorFlow ecosystem.

• Documentation
• Pretrained models

Each implementation has its own set ofunique features but shares similar goals:

• Highly configurable model architectures and training procedures
• Efficient model serving capabilities for use in real world applications
• Extensions to allow other tasks such as text generation, tagging, summarization, image to text, and speech to text

The OpenNMT ecosystem also includes projects to cover the full NMT workflow: