Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · Helsinki-NLP

opus-mt-en-iir

opus-mt-en-iir is a Marian translation model from Helsinki-NLP. According to the model card, it translates English into Indo-Iranian languages.

Publisher
Helsinki-NLP
Task
translation
Model type
marian
License
apache-2.0
Library
transformers
Publication status
Approved for indexing

Model overview

opus-mt-en-iir is published by Helsinki-NLP as a translation model. The captured configuration identifies MarianMTModel with model type marian. According to the model card, it maps English to Indo-Iranian languages with target-language selection through a sentence-initial token.

Recorded capabilities

Many-target Indo-Iranian coverage

According to the model card, one English source serves a target group spanning Assamese, Bengali, Hindi, Marathi, Urdu, Persian, Sindhi, Sinhala, Tajik, and additional listed codes.

Target-token control

According to the model card, each sentence requires an initial >>id<< token selecting a valid target language ID.

Published score tables

According to the model card, news and Tatoeba test sets report BLEU and chr-F per pair, with system metadata including training date 2020-08-01.

Use cases in the source record

  • English-to-Indo-Iranian translation across the documented target list, selected per sentence with a language token.
  • Benchmark comparison using the card's published BLEU and chr-F tables for news and Tatoeba sets.

Limitations and unknowns

  • No parameter count was extracted from this record.
  • BLEU and chr-F figures are publisher-reported benchmark claims, not independently verified.
  • Provider state is historical snapshot data, not independently refreshed current availability.

Source and provenance

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

Captured: Unknown. Processed: 2026-09-07T19:34:31.254598+00:00.

eng-iir source group: English target group: Indo-Iranian languages OPUS readme: eng-iir model: transformer source language(s): eng target language(s): asm awa ben bho gom guj hif_Latn hin jdt_Cyrl kur_Arab kur_Latn mai mar npi ori oss pan_Guru pes pes_Latn pes_Thaa pnb pus rom san_Deva sin snd_Arab tgk_Cyrl tly_Latn urd zza model: transformer 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: opus2m-2020-08-01.zip test set translations: opus2m-2020-08-01.test.txt test set scores: opus2m-2020-08-01…

F001F002F003F004F005F006F009F010F011F012F013