Started in December 2016 by the
Harvard NLP
group and
SYSTRAN
, the project has since been used in
several research and industry applications
. It is currently maintained by
SYSTRAN
and
Ubiqus
.
OpenNMT provides implementations in 2 popular deep learning frameworks:
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:
Tokenizer
Fast and customizable text tokenization library with BPE and SentencePiece support.
Documentation
OpenNMT is an open source ecosystem for neural machine translation and is licensed under the MIT license.
OpenNMT-py
Source code
Documentation
Pretrained models
OpenNMT-tf
Source code
Documentation
Pretrained models
