opus+bt-2021-04-14.zip dataset: opus+bt model: transformer-align source language(s): eng target language(s): ita model: transformer-align pre-processing: normalization + SentencePiece (spm32k,spm32k) download: opus+bt-2021-04-14.zip test set translations: opus+bt-2021-04-14.test.txt test set scores: opus+bt-2021-04-14.eval.txt Benchmarks testset BLEU chr-F #sent #words BP newssyscomb2009.eng-ita 31.3 0.608 502 11551 1.000 newstest2009.eng-ita 31.7 0.605 2525 63474 1.000 Tatoeba-test.eng-ita 48.3 0.696 10000 65500 0.957 opusTCv20210807+bt_transformer-big_2022-03-13.zip dataset: opusTCv20210807+bt model: transformer-big source language(s): eng target language(s): ita raw source language(s): eng raw target language(s): ita model: transformer-big pre-processing: normalization + SentencePiece (spm32k,spm32k) download: opusTCv20210807+bt_transformer-big_2022-03-13.zip test set translations: opusTCv20210807+bt_transformer-big_2022-03-13.test.txt test set scores: opusTCv20210807+bt_transformer-big_2022-03-13.eval.txt Benchmarks testset BLEU chr-F #sent #words BP newssyscomb2009.eng-ita 31.2 0.60759 502 11551 1.000 newstest2009.eng-ita 31.6 0.60442 2525 63474 1.000 Tatoeba-test-v2021-08-07.eng-ita 54.3 0.72878 10000 67323 0.975