README.md

opus-2020-06-17.zip

dataset: opus
model: transformer-align
source language(s): fra
target language(s): ind zsm_Latn
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)
download: opus-2020-06-17.zip
test set translations: opus-2020-06-17.test.txt
test set scores: opus-2020-06-17.eval.txt

testset	BLEU	chr-F
Tatoeba-test.fra.msa	35.3	0.617

dataset: opus
model: transformer
source language(s): fra
target language(s): ind jak msa zlm zsm
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: >>ind<< >>msa_Latn<< >>zlm_Latn<< >>jak_Latn<< >>zlm<<
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.fra-ind	37.6	0.638	900	5915	0.968
Tatoeba-test.fra-msa	35.6	0.620	998	6696	0.972
Tatoeba-test.fra-zsm_Latn	16.3	0.458	98	781	0.994