Skip to content

EthenEthenEthen

Open Source Model Profile · Helsinki-NLP

opus-mt-fi-en

opus-mt-fi-en is a Helsinki-NLP Marian model translating Finnish to English. The model card documents transformer-align preprocessing and BLEU results.

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

Model overview

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

Recorded capabilities

Finnish-to-English pair

According to the model card, the source group is Finnish and the target group is English.

Transformer-align preprocessing

The model card describes normalization plus SentencePiece preprocessing for the fin-eng configuration.

Reported newstest and Tatoeba table

According to the model card, benchmarks span multiple newstest sets plus a 53.4 BLEU Tatoeba-test result.

Use cases in the source record

  • Finnish-to-English 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-fi-en

Captured: Unknown. Processed: 2026-09-07T19:34:31.463063+00:00.

fin-eng source group: Finnish target group: English OPUS readme: fin-eng model: transformer-align source language(s): fin target language(s): eng model: transformer-align pre-processing: normalization + SentencePiece (spm32k,spm32k) download original weights: opus-2020-08-05.zip test set translations: opus-2020-08-05.test.txt test set scores: opus-2020-08-05.eval.txt Benchmarks testset BLEU chr-F newsdev2015-enfi-fineng.fin.eng 25.3 0.536 newstest2015-enfi-fineng.fin.eng 26.9 0.547 newstest2016-enfi-fineng.fin.eng 29.0 0.571 newstest2017-enfi-fineng.fin.eng 32.3 0.594 newstest2018-enfi-fineng.fin.eng 23.8 0.517 newstest2019-fien-fin…

F001F002F003F004F005F006F009F010F011