- Home
- Translation Software
- OPUS-MT
On the recordRead 12 Oct 202625 facts
OPUS-MT
Plans and prices
OPUS-MT models and services
Free
pretrained models are downloadable under CC-BY 4.0 · no commercial pricing listed
Read 12 Oct 2026 · github.com
On the record
- API access
- Yesgithub.com · read 22 Sep 2026
- API behavior
- The WebSocket client sends JSON with source text and source and target language IDs, and can request language detection by setting the source to detect or DL.github.com · read 12 Oct 2026
- Deployment
- The web application can be installed manually or with Docker, with a separate Dockerfile for CUDA GPU use.github.com · read 12 Oct 2026
- Integrations
- The project links to OPUS-CAT, which provides a local offline engine and plugins for SDL Trados Studio and memoQ, plus custom-provider use in Wordfast CAT.github.com · read 12 Oct 2026
- Known quality limits
- The project warns that many automatic evaluation scores come from simple, short Tatoeba sentences and may overstate performance on more realistic data.github.com · read 12 Oct 2026
- Language pair configuration
- The web server uses a JSON configuration to specify translation language pairs and model decoder configurations or remote hosts.github.com · read 5 Oct 2026
- License
- The OPUS-MT software repository lists the MIT license, while its downloadable pretrained translation models are listed under CC-BY 4.0.github.com · read 12 Oct 2026
- Linux service
- The project documents installing a WebSocket translation service on Ubuntu.github.com · read 5 Oct 2026
- Maintainer
- The repository belongs to the Language Technology Research Group at the University of Helsinki, whose GitHub organization lists Helsinki, Finland.github.com · read 12 Oct 2026
- Model foundation
- The models are based on Marian-NMT and trained on OPUS data using OPUS-MT-train.github.com · read 5 Oct 2026
- Model framework
- The models and services are based on Marian-NMT and are mainly segmented with SentencePiece.github.com · read 12 Oct 2026
- Model license
- The repository says its downloadable pre-trained translation models are licensed CC-BY 4.0.github.com · read 5 Oct 2026
- Model limitations
- The maintainers state that current models lack filtering, data augmentation, domain adaptation, and quality control beyond automatic evaluation on selected test sets.github.com · read 5 Oct 2026
- Privacy deployment
- The related OPUS-CAT engine is described as local and offline, intended to provide confidential machine translation on local computers.github.com · read 12 Oct 2026
- Purpose
- OPUS-MT provides open neural machine translation models and web services.github.com · read 12 Oct 2026
- Quality limitation
- The maintainers caution that many automatic evaluation scores use simple, short Tatoeba sentences and may be too optimistic for realistic data.github.com · read 5 Oct 2026
- Training environment
- The project says its model-training scripts are currently tailored to the University of Helsinki and CSC computing environment.github.com · read 12 Oct 2026
- Training limitation
- The maintainers say the model training scripts are heavily customized for the University of Helsinki and CSC computing environment.github.com · read 5 Oct 2026
