opus-tatoeba-eng-ara

Neurora/opus-tatoeba-eng-ara

opus-tatoeba-eng-ara is a translation model from Neurora. Use it when you need text moved from one language to another. The card lists the license as apache-2.0.

dataset: opus model: transformer source language(s): eng target language(s): acm afb apc ara arq ary arz model: transformer pre-processing: normalization + SentencePiece (spm32k,spm32k) a sentence initial language tok…

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

109M

219 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors217 MB · 98%

At a glance

Task: Translation
License: apache-2.0
Model type: marian
Access: Public
Created: Feb 25, 2025
Updated: Jun 6, 2025
SHA: 2c01f27f

Try a prompt

Model card

From the Hugging Face model README

Opus Tatoeba | English -> Arabic

dataset: opus
model: transformer
source language(s): eng
target language(s): acm afb apc ara arq ary arz
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)
valid language labels: >>ara<< >>ara_Latn<< >>arq_Latn<< >>arq<< >>arz<<
download: opus-2021-02-23.zip
test set translations: opus-2021-02-23.test.txt
test set scores: opus-2021-02-23.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.eng-acm	3.6	0.202	3	17	1.000
Tatoeba-test.eng-afb	29.8	0.560	36	145	1.000
Tatoeba-test.eng-apc	6.4	0.249	5	18	0.943
Tatoeba-test.eng-ara	14.0	0.437	10000	58935	1.000
Tatoeba-test.eng-arq	0.5	0.155	412	2323	1.000
Tatoeba-test.eng-ary	3.1	0.246	18	53	1.000
Tatoeba-test.eng-arz	2.1	0.249	181	856	1.000
tico19-test.eng-ara	22.2	0.530	2100	51336	0.997

Task: Translation
Type: marian
License: apache-2.0
Languages: ar, en
Created: Feb 25, 2025
Updated: Jun 6, 2025