# PyMarian: Fast Neural Machine Translation and Evaluation in Python

arXiv: https://arxiv.org/abs/2408.11853 · HTML: https://mlsanity.com/paper/2408.11853/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 11 of 11)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [Marian: Fast Neural Machine Translation in C++](https://mlsanity.com/paper/1804.00344/) (2018)
- [Scaling up COMETKIWI: Unbabel-IST 2023 Submission for the Quality Estimation Shared Task](https://mlsanity.com/paper/2309.11925/) (2023)
- [Democratizing Neural Machine Translation with OPUS-MT](https://mlsanity.com/paper/2212.01936/) (2022)
- [Unbabel's Participation in the WMT20 Metrics Shared Task](https://mlsanity.com/paper/2010.15535/) (2020)
- [Marian: Cost-effective High-Quality Neural Machine Translation in C++](https://mlsanity.com/paper/1805.12096/) (2018)
- [TranslateLocally: Blazing-fast translation running on the local CPU](https://mlsanity.com/paper/2109.10194/) (2021)

## Built on by (most cited first, 2 of 2)

- [Granary: Speech Recognition and Translation Dataset in 25 European Languages](https://mlsanity.com/paper/2505.13404/) (2025)
- [Merging Feed-Forward Sublayers for Compressed Transformers](https://mlsanity.com/paper/2501.06126/) (2025)

## Abstract (arXiv)

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 textttpip install pymarian.