opusTCv20210807_transformer-big_2022-09-15.zip dataset: opusTCv20210807 model: transformer-big source language(s): bel bel_Latn bul ces pol rus slv ukr target language(s): heb raw source language(s): bel bul ces pol rus slv ukr raw target language(s): heb model: transformer-big pre-processing: normalization + SentencePiece (spm32k,spm32k) download: opusTCv20210807_transformer-big_2022-09-15.zip test set translations: opusTCv20210807_transformer-big_2022-09-15.test.txt test set scores: opusTCv20210807_transformer-big_2022-09-15.eval.txt Benchmarks testset BLEU chr-F #sent #words BP Tatoeba-test-v2021-08-07.bel-heb 36.7 0.59808 52 271 1.000 Tatoeba-test-v2021-08-07.bul-heb 35.4 0.65393 1 3 1.000 Tatoeba-test-v2021-08-07.ces-heb 37.8 0.61586 34 201 0.970 Tatoeba-test-v2021-08-07.multi-heb 39.1 0.59285 8555 50563 0.997 Tatoeba-test-v2021-08-07.pol-heb 38.7 0.59139 5000 30233 0.993 Tatoeba-test-v2021-08-07.rus-heb 38.3 0.58388 2500 15008 1.000 Tatoeba-test-v2021-08-07.slv-heb 61.8 0.80955 2 7 1.000 Tatoeba-test-v2021-08-07.ukr-heb 43.2 0.62226 966 4796 1.000