Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-hu-en

opus-mt-hu-en is a Helsinki-NLP Marian model translating Hungarian to English. The model card documents transformer-align preprocessing and Tatoeba results.

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

Model overview

opus-mt-hu-en is published by Helsinki-NLP as a Marian translation model from Hungarian to English. The captured configuration identifies MarianMTModel with model type marian under Apache-2.0. According to the model card, it uses a transformer-align setup trained on OPUS data with normalization and SentencePiece preprocessing.

Recorded capabilities

Hungarian-to-English pair

According to the model card, the source language is hu and the target language is en.

Transformer-align preprocessing

The model card describes a transformer-align model with normalization and SentencePiece preprocessing.

Reported Tatoeba result

According to the model card, the Tatoeba benchmark is 52.9 BLEU with 0.683 chr-F.

Use cases in the source record

  • Hungarian-to-English translation workflows using a Marian text-to-text translation model.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No training hardware, context window, or quantization detail was extracted.
  • Provider state is historical snapshot data, not independently refreshed current availability.
  • Benchmark figures come from the publisher model card and were not independently verified by Ethen.

Source and provenance

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

Captured: Unknown. Processed: 2026-09-07T19:34:31.266352+00:00.

opus-mt-hu-en source languages: hu target languages: en OPUS readme: hu-en dataset: opus model: transformer-align pre-processing: normalization + SentencePiece download original weights: opus-2019-12-18.zip test set translations: opus-2019-12-18.test.txt test set scores: opus-2019-12-18.eval.txt Benchmarks testset BLEU chr-F Tatoeba.hu.en 52.9 0.683

F001F002F003F004F005F006F009F010