README.md

opus-2020-06-17.zip

testset	BLEU	chr-F
Tatoeba-test.eng.ben	16.9	0.484

dataset: opus
model: transformer
source language(s): eng
target language(s): ben
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: >>ben<< >>ben_Cyrl<< >>ben_Deva<< >>ben_Gujr<<
download: opus-2021-02-23.zip
test set translations: opus-2021-02-23.test.txt
test set scores: opus-2021-02-23.eval.txt

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.eng-ben	16.6	0.481	2500	11654	1.000
tico19-test.eng-ben	5.6	0.327	2100	51751	0.833

dataset: opus+bt
model: transformer-align
source language(s): eng
target language(s): ben
model: transformer-align
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: >>ben<< >>ben_Cyrl<< >>ben_Deva<< >>ben_Gujr<<
download: opus+bt-2021-04-10.zip
test set translations: opus+bt-2021-04-10.test.txt
test set scores: opus+bt-2021-04-10.eval.txt

testset	BLEU	chr-F	#sent	#words	BP
Tatoeba-test.eng-ben	17.3	0.487	2500	11654	1.000
tico19-test.eng-ben	5.9	0.334	2100	51751	0.837