Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-ur-en

opus-mt-ur-en is an Urdu-to-English machine-translation model from Helsinki-NLP. According to the model card, it is a transformer-align model with SentencePiece preprocessing reporting BLEU 23.2 on Tatoeba.

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

Model overview

opus-mt-ur-en is published by Helsinki-NLP for translation from Urdu (ur) to English (en). The captured configuration identifies MarianMTModel with model type marian and Transformers library support. According to the model card, the model is a transformer-align model from the Tatoeba-Challenge urd-eng pair using normalization and SentencePiece preprocessing.

Recorded capabilities

Urdu-to-English pair

Hub tags record ur and en language support, and the model card lists the Urdu source group with an English target group.

MarianMT with SentencePiece

The captured configuration identifies MarianMTModel with model type marian, and the model card documents transformer-align training with normalization and SentencePiece (spm32k, spm32k) preprocessing.

Reported Tatoeba scores

According to the model card, the model reports BLEU 23.2 and chr-F 0.435 on the Tatoeba-test.urd.eng set, with training dated 2020-06-17.

Use cases in the source record

  • Urdu-to-English translation within Transformers text2text-generation workflows.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • No context-window value was extracted from this record.
  • Benchmark figures are publisher-reported test-set scores and were not independently verified by Ethen.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.

Source and provenance

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

Captured: Unknown. Processed: 2026-09-07T19:34:31.544756+00:00.

urd-eng source group: Urdu target group: English OPUS readme: urd-eng model: transformer-align source language(s): urd target language(s): eng 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.urd.eng 23.2 0.435 System Info: hf_name: urd-eng source_languages: urd target_languages: eng opus_readme_url: https://github.com/Helsinki-NLP/Tatoeba-Challenge/tree/master/models/urd-eng/README.md original_repo: Tatoeba-Challenge…

F001F002F003F004F005F006F007F008F009F010F011