Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-en-vi

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

Recorded capabilities

English-to-Vietnamese pair

According to the model card, the source group is English and the target group is Vietnamese, including vie and vie_Hani targets.

Transformer-align preprocessing

The model card describes normalization plus SentencePiece preprocessing and a sentence-initial language token requirement.

Reported Tatoeba result

According to the model card, the Tatoeba-test result is 37.2 BLEU with 0.542 chr-F.

Use cases in the source record

  • English-to-Vietnamese 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 and system details come from the publisher model card and were not independently verified by Ethen.

Source and provenance

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

Captured: Unknown. Processed: 2026-09-07T19:34:31.417039+00:00.

eng-vie source group: English target group: Vietnamese OPUS readme: eng-vie model: transformer-align source language(s): eng target language(s): vie vie_Hani model: transformer-align pre-processing: normalization + SentencePiece (spm32k,spm32k) a sentence initial language token is required in the form of >>id<< (id = valid target language ID) download original weights: opus-2020-06-17.zip test set translations: opus-2020-06-17.test.txt test set scores: opus-2020-06-17.eval.txt Benchmarks testset BLEU chr-F Tatoeba-test.eng.vie 37.2 0.542 System Info: hf_name: eng-vie source_languages: eng target_languages: vie opus_readme_url: https…

F001F002F003F004F005F006F009F010F011