Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-ko-es

opus-mt-ko-es is a Helsinki-NLP Marian translation model for Korean-to-Spanish. Its model card reports a transformer-align setup with BLEU 31.3 and chrF 0.521 on a Tatoeba test set.

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

Model overview

opus-mt-ko-es is published by Helsinki-NLP as a translation model. The captured configuration identifies MarianMTModel with model type marian. According to the model card, it covers the kor-spa pair with normalization plus SentencePiece preprocessing.

Recorded capabilities

Korean-to-Spanish pair

According to the model card, the source group is Korean and the target group is Spanish, tagged ko and es.

Documented preprocessing

The publisher describes normalization plus SentencePiece with spm32k vocabularies on both sides.

Reported Tatoeba scores

The model card reports BLEU 31.3 and chrF2 0.521 on Tatoeba-test.kor.spa, with additional brevity and reference-length detail.

Use cases in the source record

  • Korean-to-Spanish text translation of the kind documented in the publisher's kor-spa materials.
  • Translation research that references the card's reported Tatoeba BLEU and chrF scores and preprocessing setup.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No context-window value was extracted from this record.
  • Benchmark figures above are publisher-reported card values, not Ethen-measured results.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

Source: Helsinki-NLP/opus-mt-ko-es

Captured: Unknown. Processed: 2026-09-07T19:34:31.319289+00:00.

kor-spa source group: Korean target group: Spanish OPUS readme: kor-spa model: transformer-align source language(s): kor kor_Hang kor_Latn target language(s): spa model: transformer-align pre-processing: normalization + SentencePiece (spm32k,spm32k) 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.kor.spa 31.3 0.521 System Info: hf_name: kor-spa source_languages: kor target_languages: spa opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/kor-spa/README.md original_repo…

F001F002F003F004F005F006F007F008F009F010F011