The Neural Machine Translation (NMT) models downloadable from this page are in-domain models, which means they are trained and tested only on specialized data, and they can act better than generic models for the specified "domain". In other words, in-domain models can observe terminology and generate translations that are much more in line with the specialized context.
There are three methods to use the downloadable pre-trained NMT models.
You can use OpenNMT-py (PyTorch version) from the command line as follows:
python3 OpenNMT-py/translate.py -model model.pt -src source.txt -output target.txt -replace_unk
You can run a simple OpenNMT-py REST API.
You can use a stand-alone executable GUI. It is still basic, but it works. Currently, I (Yasmin) is working on improving the GUI translator and expanding its features. If you have suggestions, please feel free to contact me.
Currently, all the models on this page are created using OpenNMT-py, based on PyTorch.
For internal use only. For research, please attribute:
Yasmin Moslem, 2020, OpenNMT-py Pre-trained Models, MachineTranslation.io
|Configuration||OpenNMT-Py RNN-LSTM default options|
|Data||MS ≈500k segments|
|Configuration||OpenNMT-Py Transformer standard options - 140k steps|
|Data||UN Corpus ≈20m segments|
|Configuration||OpenNMT-Py Transformer standard options|
|Data||MultiUN ≈13m segments|