opus+bt-2021-04-14.zip dataset: opus+bt model: transformer-align source language(s): eng target language(s): lit 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 newsdev2019-enlt.eng-lit 24.1 0.564 2000 40116 1.000 newstest2019-enlt.eng-lit 15.0 0.486 998 20091 1.000 Tatoeba-test.eng-lit 39.0 0.671 2500 14798 0.939 opusTCv20210807+bt_transformer-big_2022-02-25.zip dataset: opusTCv20210807+bt model: transformer-big source language(s): eng target language(s): lit raw source language(s): eng raw target language(s): lit model: transformer-big pre-processing: normalization + SentencePiece (spm32k,spm32k) download: opusTCv20210807+bt_transformer-big_2022-02-25.zip test set translations: opusTCv20210807+bt_transformer-big_2022-02-25.test.txt test set scores: opusTCv20210807+bt_transformer-big_2022-02-25.eval.txt Benchmarks testset BLEU chr-F #sent #words BP newsdev2019-enlt.eng-lit 27.2 0.58648 2000 40116 1.000 newstest2019-enlt.eng-lit 18.3 0.51863 998 20091 1.000 Tatoeba-test-v2021-08-07.eng-lit 39.4 0.67423 2528 14942 0.962