OpusDistillery: A Configurable End-to-End Pipeline for Systematic Multilingual Distillation of Open NMT Models
Year: 2025
Type: article
Abstract: In this work, we introduce OpusDistillery, a novel framework to streamline the Knowledge Distillation (KD) process of multilingual NMT models. OpusDistillery's main features are the integration of openly available teacher models from OPUS-MT and Hugging Face, comprehensive multilingual support and robust GPU utilization tracking. We describe the tool in detail and discuss the individual contributions of its pipeline components, demonstrating its flexibility for different use cases. OpusDistillery is open-source and released under a permissive license, aiming to facilitate further research and development in the field of multilingual KD for any sequence-to-sequence task. Our code is available at https://github.com/Helsinki-NLP/OpusDistillery.
Authors: Gibert, Ona de, Nieminen, Tommi, Scherrer, Yves, Tiedemann, Jörg
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6986189862
FWCI:
Cites:
Cited by:
Related to: