Fine-tuning Meta models improves German English translation quality
Dataset Collection and Fine-Tuning of NLLB for German--English Translation
Computation and Language
Summary
Translating between German and English can be tricky, especially for books and technical documents. The authors gathered a carefully cleaned set of German-English sentence pairs from a public collection and used it to improve an existing Meta AI translation model. Their updated model translates texts better in both style and accuracy. They also integrated this improved tool into an open translation system that works well with popular document formats like PDFs and Office files. All the steps and code are shared to let others reproduce and use their work.
What this means in practice
- •For software developers: Use the improved German-English translation model for document translation systems that preserve original formatting in PDFs and Office files.
- •For localization teams: Integrate the fine-tuned model to produce higher-quality translations of literary and technical German texts into English.$Commercial implications: Enables offering enhanced translation services for German-English content with better accuracy and style.
Authors
SK Deeraj, Yash Ingle, Pruthwik Mishra
Abstract
This paper describes the curation of a high-quality parallel corpus from OPUS Books and the fine-tuning of Meta's NLLB-200 models for German--English translation. We detail a dataset extraction pipeline that filters 45k raw OPUS sentence pairs to 25k high-quality examples through encoding validation, length filtering, language identification, deduplication, and quality scoring. We present a reproducible fine-tuning methodology optimized for consumer GPUs using mixed precision, gradient accumulation, and gradient checkpointing. Our fine-tuned NLLB-600M model achieves statistically significant improvements (+3.4 BLEU, +2.6 chrF++, -3.2 TER) over the base model on literary and technical German-English translation. We demonstrate practical deployment by integrating the fine-tuned model into LinguaHaru, an existing open-source document translation system, achieving format-preserving translation across PDF and Office documents. All dataset preparation scripts, training code, and evaluation tools are provided for reproducibility. The fine-tuned model is available at HuggingFace.