This package includes scripts for training NMT models using MarianNMT and OPUS data for [OPUS-MT](https://github.com/Helsinki-NLP/Opus-MT). More details are given in the [Makefile](Makefile) but documentation needs to be improved. Also, the targets require a specific environment and right now only work well on the CSC HPC cluster in Finland.
The subdirectory [models](https://github.com/Helsinki-NLP/Opus-MT-train/tree/master/models) contains information about pre-trained models that can be downloaded from this project. They are distribted with a [CC-BY 4.0 license](https://creativecommons.org/licenses/by/4.0/) license. [More pre-trained models](https://github.com/Helsinki-NLP/Tatoeba-Challenge/blob/master/results/tatoeba-results-all.md) trained with the [OPUS-MT training pipeline](https://github.com/Helsinki-NLP/OPUS-MT-train/blob/master/doc/TatoebaChallenge.md) are available from the [Tatoeba translation challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge) also under a [CC-BY 4.0 license](https://creativecommons.org/licenses/by/4.0/) license.
For CSC-users: adjust `lib/env/puhti.mk` and `lib/env/mahti.mk` to match yoursetup (especially the locations where Marian-NMT and other tools are installed and the CSC project that you are using).
We would also like to acknowledge the support by the [University of Helsinki](https://blogs.helsinki.fi/language-technology/), the [IT Center of Science CSC](https://www.csc.fi/en/home), the funding through projects in the EU Horizon 2020 framework ([FoTran](http://www.helsinki.fi/fotran), [MeMAD](https://memad.eu/), [ELG](https://www.european-language-grid.eu/)) and the contributors to the open collection of parallel corpora [OPUS](http://opus.nlpl.eu/).