ara-heb

opus-2020-06-18.zip

• dataset: opus
• model: transformer
• source language(s): apc apc_Latn ara arq arz
• target language(s): heb
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• download: opus-2020-06-18.zip
• test set translations: opus-2020-06-18.test.txt
• test set scores: opus-2020-06-18.eval.txt

Benchmarks

testset	BLEU	chr-F
Tatoeba-test.ara.heb	40.6	0.604

opus-2021-02-23.zip

• dataset: opus
• model: transformer
• source language(s): apc ara arq arz
• target language(s): heb
• model: transformer
• pre-processing: normalization + SentencePiece (spm32k,spm32k)
• 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.apc-heb	42.7	0.559	1	5	1.000
Tatoeba-test.ara-heb	40.4	0.605	1208	6801	1.000
Tatoeba-test.arq-heb	10.7	0.388	1	4	1.000
Tatoeba-test.arz-heb	23.6	0.654	2	10	1.000