Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-bg-en

opus-mt-bg-en is a MarianMT translation model from Helsinki-NLP for Bulgarian-to-English text. Its model card documents OPUS data, SentencePiece preprocessing, and Tatoeba BLEU and chr-F scores.

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

Model overview

opus-mt-bg-en is published by Helsinki-NLP as a translation model. The captured configuration identifies MarianMTModel with a marian model type and a transformers library tag. According to the model card, it maps Bulgarian source text to English targets using OPUS data with normalization and SentencePiece preprocessing.

Recorded capabilities

Bulgarian-to-English pair

According to the model card, the model covers Bulgarian source text and English targets.

MarianMT architecture

Captured configuration identifies MarianMTModel with a marian model type.

OPUS data and SentencePiece notes

The model card documents OPUS data, a transformer-align setup, and normalization plus SentencePiece preprocessing.

Publisher-reported Tatoeba scores

According to the model card, the model reports BLEU 59.4 and chr-F 0.727 on the Tatoeba.bg.en test set.

Use cases in the source record

  • Bulgarian-to-English translation workflows that use the documented bg-to-en language pair.
  • OPUS-based translation experiments that follow the model card's normalization and SentencePiece preprocessing notes.

Limitations and unknowns

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

Source and provenance

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

Captured: Unknown. Processed: 2026-09-07T19:34:31.241247+00:00.

opus-mt-bg-en source languages: bg target languages: en OPUS readme: bg-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.bg.en 59.4 0.727

F001F002F003F004F005F006F007F008F009F010