PyMarian: Fast Neural Machine Translation and Evaluation in Python
Abstract
The deep learning language of choice these days is Python; measured by factors such as available libraries and technical support, it is hard to beat. At the same time, software written in lower-level programming languages like C++ retain advantages in speed. We describe a Python interface to Marian NMT, a C++-based training and inference toolkit for sequence-to-sequence models, focusing on machine translation. This interface enables models trained with Marian to be connected to the rich, wide range of tools available in Python. A highlight of the interface is the ability to compute state-of-the-art COMET metrics from Python but using Marian's inference engine, with a speedup factor of up to 7.8 the existing implementations. We also briefly spotlight a number of other integrations, including Jupyter notebooks, connection with prebuilt models, and a web app interface provided with the package. PyMarian is available in PyPI via .
Cite
@article{arxiv.2408.11853,
title = {PyMarian: Fast Neural Machine Translation and Evaluation in Python},
author = {Thamme Gowda and Roman Grundkiewicz and Elijah Rippeth and Matt Post and Marcin Junczys-Dowmunt},
journal= {arXiv preprint arXiv:2408.11853},
year = {2024}
}