Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-et-en

opus-mt-et-en is a Marian translation model from Helsinki-NLP. According to the model card, it translates Estonian to English with reported BLEU scores.

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

Model overview

opus-mt-et-en is published by Helsinki-NLP as a translation model. The captured configuration identifies MarianMTModel with model type marian. According to the model card, it translates Estonian to English using OPUS data with SentencePiece pre-processing.

Recorded capabilities

Estonian-to-English translation

According to the model card, the model translates Estonian source text to English target text.

Marian with Transformers

The captured configuration reports MarianMTModel with model type marian and Transformers library support.

Reported BLEU and chr-F scores

According to the model card, reported scores include 30.1 BLEU on newsdev2018, 30.3 on newstest2018, and 59.9 on Tatoeba.

OPUS data with SentencePiece

According to the model card, the model uses OPUS data with normalization plus SentencePiece pre-processing.

Use cases in the source record

  • Estonian-to-English neural machine translation workflows.
  • Transformers translation experiments using the documented OPUS and SentencePiece-based Marian setup.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • Benchmark figures are publisher-reported card values and have not been independently verified by Ethen.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

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

Captured: Unknown. Processed: 2026-09-07T19:34:31.456493+00:00.

opus-mt-et-en source languages: et target languages: en OPUS readme: et-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 newsdev2018-enet.et.en 30.1 0.574 newstest2018-enet.et.en 30.3 0.581 Tatoeba.et.en 59.9 0.738

F001F002F003F004F005F006F007F009F010