English-to-Romance multilingual model
According to the model card, the model translates English into Romance languages with target-side multilingual coverage and SentencePiece spm32k pre-processing.
Open Source Model Profile · Helsinki-NLP
opus-mt-en-roa
opus-mt-en-roa is a Helsinki-NLP Marian model for English-to-Romance-language translation. According to the model card, it needs a sentence-initial target-language token.
- Publisher
- Helsinki-NLP
- Task
- translation
- Model type
- marian
- License
- apache-2.0
- Library
- transformers
- Publication status
- Approved for indexing
Model overview
opus-mt-en-roa is published by Helsinki-NLP as a Marian translation model. The captured configuration identifies MarianMTModel with model type marian, and card data records an apache-2.0 license. According to the model card, it translates English into Romance languages with a transformer model and SentencePiece pre-processing.
Recorded capabilities
Marian Transformers design
Captured configuration identifies MarianMTModel with model type marian, and the hub lists Transformers support with pytorch, tf, and rust tags.
Extensive reported benchmarks
According to the model card, the publisher reports news and Tatoeba BLEU and chr-F scores across many English-Romance pairs.
Use cases in the source record
- English-to-Romance-language translation work where the publisher-documented language token selects the target language.
- Transformers-based multilingual translation experiments following the publisher's SentencePiece and OPUS-readme description.
Limitations and unknowns
- No Ethen-measured evaluation results were extracted from this record.
- No parameter count was extracted.
- Provider state is historical snapshot data and should be refreshed before being presented as current.
- Language coverage and score claims are publisher model-card statements and were not independently verified by Ethen.
Source and provenance
Source: Helsinki-NLP/opus-mt-en-roa
Captured: Unknown. Processed: 2026-09-07T19:34:31.364336+00:00.
eng-roa source group: English target group: Romance languages OPUS readme: eng-roa model: transformer source language(s): eng target language(s): arg ast cat cos egl ext fra frm_Latn gcf_Latn glg hat ind ita lad lad_Latn lij lld_Latn lmo max_Latn mfe min mwl oci pap pms por roh ron scn spa tmw_Latn vec wln zlm_Latn zsm_Latn 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…
F001F002F003F004F005F006F007F009F010F011F012F013