opus-2021-05-15.zip

dataset: opus
model: transformer-align
source language(s): ell
target language(s): rus
model: transformer-align
pre-processing: normalization + SentencePiece (spm32k,spm32k)
download: opus-2021-05-15.zip
test set translations: opus-2021-05-15.test.txt
test set scores: opus-2021-05-15.eval.txt

Benchmarks

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.ell-rus	54.7	0.722	2500	14600	0.992