opus-2021-02-19.zip dataset: opus model: transformer source language(s): ces target language(s): spa model: transformer pre-processing: normalization + SentencePiece (spm32k,spm32k) download: opus-2021-02-19.zip test set translations: opus-2021-02-19.test.txt test set scores: opus-2021-02-19.eval.txt Benchmarks testset BLEU chr-F #sent #words BP newssyscomb2009.ces-spa 27.0 0.548 502 12506 0.980 news-test2008.ces-spa 24.8 0.531 2051 52596 0.983 newstest2009.ces-spa 25.3 0.540 2525 68114 0.988 newstest2010.ces-spa 29.0 0.563 2489 65522 0.991 newstest2011.ces-spa 29.5 0.556 3003 79476 0.987 newstest2012.ces-spa 28.8 0.554 3003 79006 0.986 newstest2013.ces-spa 29.8 0.556 3000 70528 0.963 Tatoeba-test.ces-spa 53.4 0.706 1807 12716 0.971