Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-de-en

opus-mt-de-en is a MarianMT translation model from Helsinki-NLP for German-to-English text with OPUS data provenance.

Publisher
Helsinki-NLP
Task
translation
Model type
marian
License
apache-2.0
Library
transformers
Publication status
Accepted · not indexed

Model overview

opus-mt-de-en is published by Helsinki-NLP as a translation model. Captured configuration identifies MarianMTModel with a marian model type under Apache-2.0. According to the model card, it handles German-to-English translation with OPUS dataset provenance and SentencePiece preprocessing.

Recorded capabilities

German-to-English direction

According to the model card, the source language is German and the target language is English.

MarianMT architecture

Captured configuration records MarianMTModel with a marian model type for translation.

OPUS transformer-align provenance

The model card identifies OPUS data, a transformer-align model, normalization plus SentencePiece preprocessing, and named original weights.

Published BLEU and chr-F table

According to the model card, BLEU and chr-F figures are listed across news-test sets from 2008 through 2019 and Tatoeba.

Use cases in the source record

  • German-to-English translation workflows using the publisher-documented source and target language direction.
  • Text-to-text generation experiments consistent with the recorded translation and text2text-generation tags.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No context-window value was extracted from this record.
  • Provider state is historical snapshot data and should be refreshed before being presented as current availability.
  • Benchmark figures come from the publisher model card and have not been independently verified by Ethen.

Source and provenance

Source: Helsinki-NLP/opus-mt-de-en

Captured: Unknown. Processed: 2026-09-07T19:34:31.278925+00:00.

opus-mt-de-en source languages: de target languages: en OPUS readme: de-en dataset: opus model: transformer-align pre-processing: normalization + SentencePiece download original weights: opus-2020-02-26.zip test set translations: opus-2020-02-26.test.txt test set scores: opus-2020-02-26.eval.txt Benchmarks testset BLEU chr-F newssyscomb2009.de.en 29.4 0.557 news-test2008.de.en 27.8 0.548 newstest2009.de.en 26.8 0.543 newstest2010.de.en 30.2 0.584 newstest2011.de.en 27.4 0.556 newstest2012.de.en 29.1 0.569 newstest2013.de.en 32.1 0.583 newstest2014-deen.de.en 34.0 0.600 newstest2015-ende.de.en 34.2 0.599 newstest2016-ende.de.en 40.4…

F001F002F003F004F005F006F008F009F010