--- library_name: transformers language: - af - ang - bar - bi - bzj - de - djk - drt - en - enm - es - fr - frr - fy - gos - gsw - hrx - hwc - icr - jam - kri - ksh - lb - li - nds - nl - ofs - pcm - pdc - pfl - pih - pis - pt - rop - sco - srm - srn - stq - swg - tcs - tpi - vls - wae - yi - zea tags: - translation - opus-mt-tc-bible license: apache-2.0 model-index: - name: opus-mt-tc-bible-big-gmw-deu_eng_fra_por_spa results: - task: name: Translation afr-deu type: translation args: afr-deu dataset: name: flores200-devtest type: flores200-devtest args: afr-deu metrics: - name: BLEU type: bleu value: 29.5 - name: chr-F type: chrf value: 0.58456 - task: name: Translation afr-eng type: translation args: afr-eng dataset: name: flores200-devtest type: flores200-devtest args: afr-eng metrics: - name: BLEU type: bleu value: 54.7 - name: chr-F type: chrf value: 0.74857 - task: name: Translation afr-fra type: translation args: afr-fra dataset: name: flores200-devtest type: flores200-devtest args: afr-fra metrics: - name: BLEU type: bleu value: 37.2 - name: chr-F type: chrf value: 0.62537 - task: name: Translation afr-por type: translation args: afr-por dataset: name: flores200-devtest type: flores200-devtest args: afr-por metrics: - name: BLEU type: bleu value: 36.1 - name: chr-F type: chrf value: 0.61751 - task: name: Translation afr-spa type: translation args: afr-spa dataset: name: flores200-devtest type: flores200-devtest args: afr-spa metrics: - name: BLEU type: bleu value: 23.2 - name: chr-F type: chrf value: 0.51647 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: flores200-devtest type: flores200-devtest args: deu-eng metrics: - name: BLEU type: bleu value: 41.4 - name: chr-F type: chrf value: 0.67103 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: flores200-devtest type: flores200-devtest args: deu-fra metrics: - name: BLEU type: bleu value: 36.8 - name: chr-F type: chrf value: 0.62658 - task: name: Translation deu-por type: translation args: deu-por dataset: name: flores200-devtest type: flores200-devtest args: deu-por metrics: - name: BLEU type: bleu value: 34.8 - name: chr-F type: chrf value: 0.60909 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: flores200-devtest type: flores200-devtest args: deu-spa metrics: - name: BLEU type: bleu value: 24.2 - name: chr-F type: chrf value: 0.52584 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: flores200-devtest type: flores200-devtest args: eng-deu metrics: - name: BLEU type: bleu value: 37.5 - name: chr-F type: chrf value: 0.64560 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: flores200-devtest type: flores200-devtest args: eng-fra metrics: - name: BLEU type: bleu value: 49.1 - name: chr-F type: chrf value: 0.70736 - task: name: Translation eng-por type: translation args: eng-por dataset: name: flores200-devtest type: flores200-devtest args: eng-por metrics: - name: BLEU type: bleu value: 49.5 - name: chr-F type: chrf value: 0.71065 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: flores200-devtest type: flores200-devtest args: eng-spa metrics: - name: BLEU type: bleu value: 27.4 - name: chr-F type: chrf value: 0.55738 - task: name: Translation lim-deu type: translation args: lim-deu dataset: name: flores200-devtest type: flores200-devtest args: lim-deu metrics: - name: BLEU type: bleu value: 16.1 - name: chr-F type: chrf value: 0.45062 - task: name: Translation lim-eng type: translation args: lim-eng dataset: name: flores200-devtest type: flores200-devtest args: lim-eng metrics: - name: BLEU type: bleu value: 21.8 - name: chr-F type: chrf value: 0.48217 - task: name: Translation lim-fra type: translation args: lim-fra dataset: name: flores200-devtest type: flores200-devtest args: lim-fra metrics: - name: BLEU type: bleu value: 18.5 - name: chr-F type: chrf value: 0.44347 - task: name: Translation lim-por type: translation args: lim-por dataset: name: flores200-devtest type: flores200-devtest args: lim-por metrics: - name: BLEU type: bleu value: 16.8 - name: chr-F type: chrf value: 0.42527 - task: name: Translation lim-spa type: translation args: lim-spa dataset: name: flores200-devtest type: flores200-devtest args: lim-spa metrics: - name: BLEU type: bleu value: 13.6 - name: chr-F type: chrf value: 0.39232 - task: name: Translation ltz-deu type: translation args: ltz-deu dataset: name: flores200-devtest type: flores200-devtest args: ltz-deu metrics: - name: BLEU type: bleu value: 31.3 - name: chr-F type: chrf value: 0.60114 - task: name: Translation ltz-eng type: translation args: ltz-eng dataset: name: flores200-devtest type: flores200-devtest args: ltz-eng metrics: - name: BLEU type: bleu value: 39.3 - name: chr-F type: chrf value: 0.64345 - task: name: Translation ltz-fra type: translation args: ltz-fra dataset: name: flores200-devtest type: flores200-devtest args: ltz-fra metrics: - name: BLEU type: bleu value: 33.8 - name: chr-F type: chrf value: 0.59368 - task: name: Translation ltz-por type: translation args: ltz-por dataset: name: flores200-devtest type: flores200-devtest args: ltz-por metrics: - name: BLEU type: bleu value: 24.8 - name: chr-F type: chrf value: 0.51545 - task: name: Translation ltz-spa type: translation args: ltz-spa dataset: name: flores200-devtest type: flores200-devtest args: ltz-spa metrics: - name: BLEU type: bleu value: 17.5 - name: chr-F type: chrf value: 0.44821 - task: name: Translation nld-deu type: translation args: nld-deu dataset: name: flores200-devtest type: flores200-devtest args: nld-deu metrics: - name: BLEU type: bleu value: 22.4 - name: chr-F type: chrf value: 0.53650 - task: name: Translation nld-eng type: translation args: nld-eng dataset: name: flores200-devtest type: flores200-devtest args: nld-eng metrics: - name: BLEU type: bleu value: 30.6 - name: chr-F type: chrf value: 0.59102 - task: name: Translation nld-fra type: translation args: nld-fra dataset: name: flores200-devtest type: flores200-devtest args: nld-fra metrics: - name: BLEU type: bleu value: 28.7 - name: chr-F type: chrf value: 0.56608 - task: name: Translation nld-por type: translation args: nld-por dataset: name: flores200-devtest type: flores200-devtest args: nld-por metrics: - name: BLEU type: bleu value: 26.7 - name: chr-F type: chrf value: 0.54728 - task: name: Translation nld-spa type: translation args: nld-spa dataset: name: flores200-devtest type: flores200-devtest args: nld-spa metrics: - name: BLEU type: bleu value: 20.1 - name: chr-F type: chrf value: 0.49175 - task: name: Translation tpi-deu type: translation args: tpi-deu dataset: name: flores200-devtest type: flores200-devtest args: tpi-deu metrics: - name: BLEU type: bleu value: 10.9 - name: chr-F type: chrf value: 0.40350 - task: name: Translation tpi-eng type: translation args: tpi-eng dataset: name: flores200-devtest type: flores200-devtest args: tpi-eng metrics: - name: BLEU type: bleu value: 19.6 - name: chr-F type: chrf value: 0.48289 - task: name: Translation tpi-fra type: translation args: tpi-fra dataset: name: flores200-devtest type: flores200-devtest args: tpi-fra metrics: - name: BLEU type: bleu value: 16.1 - name: chr-F type: chrf value: 0.43428 - task: name: Translation tpi-por type: translation args: tpi-por dataset: name: flores200-devtest type: flores200-devtest args: tpi-por metrics: - name: BLEU type: bleu value: 15.4 - name: chr-F type: chrf value: 0.42966 - task: name: Translation tpi-spa type: translation args: tpi-spa dataset: name: flores200-devtest type: flores200-devtest args: tpi-spa metrics: - name: BLEU type: bleu value: 12.9 - name: chr-F type: chrf value: 0.39730 - task: name: Translation afr-deu type: translation args: afr-deu dataset: name: flores101-devtest type: flores_101 args: afr deu devtest metrics: - name: BLEU type: bleu value: 28.4 - name: chr-F type: chrf value: 0.57831 - task: name: Translation afr-eng type: translation args: afr-eng dataset: name: flores101-devtest type: flores_101 args: afr eng devtest metrics: - name: BLEU type: bleu value: 53.8 - name: chr-F type: chrf value: 0.74272 - task: name: Translation afr-fra type: translation args: afr-fra dataset: name: flores101-devtest type: flores_101 args: afr fra devtest metrics: - name: BLEU type: bleu value: 36.4 - name: chr-F type: chrf value: 0.61936 - task: name: Translation afr-por type: translation args: afr-por dataset: name: flores101-devtest type: flores_101 args: afr por devtest metrics: - name: BLEU type: bleu value: 35.4 - name: chr-F type: chrf value: 0.61309 - task: name: Translation afr-spa type: translation args: afr-spa dataset: name: flores101-devtest type: flores_101 args: afr spa devtest metrics: - name: BLEU type: bleu value: 22.9 - name: chr-F type: chrf value: 0.51393 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: flores101-devtest type: flores_101 args: deu spa devtest metrics: - name: BLEU type: bleu value: 23.9 - name: chr-F type: chrf value: 0.52438 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: flores101-devtest type: flores_101 args: eng deu devtest metrics: - name: BLEU type: bleu value: 37.2 - name: chr-F type: chrf value: 0.64236 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: flores101-devtest type: flores_101 args: eng spa devtest metrics: - name: BLEU type: bleu value: 27.1 - name: chr-F type: chrf value: 0.55524 - task: name: Translation nld-deu type: translation args: nld-deu dataset: name: flores101-devtest type: flores_101 args: nld deu devtest metrics: - name: BLEU type: bleu value: 22.1 - name: chr-F type: chrf value: 0.53435 - task: name: Translation nld-eng type: translation args: nld-eng dataset: name: flores101-devtest type: flores_101 args: nld eng devtest metrics: - name: BLEU type: bleu value: 30.0 - name: chr-F type: chrf value: 0.58686 - task: name: Translation nld-fra type: translation args: nld-fra dataset: name: flores101-devtest type: flores_101 args: nld fra devtest metrics: - name: BLEU type: bleu value: 28.2 - name: chr-F type: chrf value: 0.56292 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: generaltest2022 type: generaltest2022 args: deu-eng metrics: - name: BLEU type: bleu value: 31.0 - name: chr-F type: chrf value: 0.56042 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: generaltest2022 type: generaltest2022 args: deu-fra metrics: - name: BLEU type: bleu value: 37.6 - name: chr-F type: chrf value: 0.61145 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: generaltest2022 type: generaltest2022 args: eng-deu metrics: - name: BLEU type: bleu value: 32.5 - name: chr-F type: chrf value: 0.60090 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: multi30k_test_2016_flickr type: multi30k-2016_flickr args: deu-eng metrics: - name: BLEU type: bleu value: 40.1 - name: chr-F type: chrf value: 0.60974 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: multi30k_test_2016_flickr type: multi30k-2016_flickr args: deu-fra metrics: - name: BLEU type: bleu value: 38.8 - name: chr-F type: chrf value: 0.62493 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: multi30k_test_2016_flickr type: multi30k-2016_flickr args: eng-deu metrics: - name: BLEU type: bleu value: 35.3 - name: chr-F type: chrf value: 0.64164 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: multi30k_test_2016_flickr type: multi30k-2016_flickr args: eng-fra metrics: - name: BLEU type: bleu value: 50.7 - name: chr-F type: chrf value: 0.71137 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: multi30k_test_2017_flickr type: multi30k-2017_flickr args: deu-eng metrics: - name: BLEU type: bleu value: 40.6 - name: chr-F type: chrf value: 0.63118 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: multi30k_test_2017_flickr type: multi30k-2017_flickr args: deu-fra metrics: - name: BLEU type: bleu value: 37.0 - name: chr-F type: chrf value: 0.62614 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: multi30k_test_2017_flickr type: multi30k-2017_flickr args: eng-deu metrics: - name: BLEU type: bleu value: 33.4 - name: chr-F type: chrf value: 0.62518 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: multi30k_test_2017_flickr type: multi30k-2017_flickr args: eng-fra metrics: - name: BLEU type: bleu value: 50.3 - name: chr-F type: chrf value: 0.71402 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: multi30k_test_2017_mscoco type: multi30k-2017_mscoco args: deu-eng metrics: - name: BLEU type: bleu value: 32.1 - name: chr-F type: chrf value: 0.55495 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: multi30k_test_2017_mscoco type: multi30k-2017_mscoco args: deu-fra metrics: - name: BLEU type: bleu value: 34.7 - name: chr-F type: chrf value: 0.59307 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: multi30k_test_2017_mscoco type: multi30k-2017_mscoco args: eng-deu metrics: - name: BLEU type: bleu value: 29.7 - name: chr-F type: chrf value: 0.58028 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: multi30k_test_2017_mscoco type: multi30k-2017_mscoco args: eng-fra metrics: - name: BLEU type: bleu value: 54.7 - name: chr-F type: chrf value: 0.73637 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: multi30k_test_2018_flickr type: multi30k-2018_flickr args: deu-eng metrics: - name: BLEU type: bleu value: 36.7 - name: chr-F type: chrf value: 0.59367 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: multi30k_test_2018_flickr type: multi30k-2018_flickr args: deu-fra metrics: - name: BLEU type: bleu value: 31.3 - name: chr-F type: chrf value: 0.57388 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: multi30k_test_2018_flickr type: multi30k-2018_flickr args: eng-deu metrics: - name: BLEU type: bleu value: 30.8 - name: chr-F type: chrf value: 0.59998 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: multi30k_test_2018_flickr type: multi30k-2018_flickr args: eng-fra metrics: - name: BLEU type: bleu value: 41.6 - name: chr-F type: chrf value: 0.65354 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newsdiscusstest2015 type: newsdiscusstest2015 args: eng-fra metrics: - name: BLEU type: bleu value: 37.7 - name: chr-F type: chrf value: 0.63308 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstestALL2020 type: newstestALL2020 args: deu-eng metrics: - name: BLEU type: bleu value: 34.5 - name: chr-F type: chrf value: 0.60800 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstestALL2020 type: newstestALL2020 args: eng-deu metrics: - name: BLEU type: bleu value: 31.7 - name: chr-F type: chrf value: 0.60078 - task: name: Translation afr-deu type: translation args: afr-deu dataset: name: ntrex128 type: ntrex128 args: afr-deu metrics: - name: BLEU type: bleu value: 25.8 - name: chr-F type: chrf value: 0.55289 - task: name: Translation afr-eng type: translation args: afr-eng dataset: name: ntrex128 type: ntrex128 args: afr-eng metrics: - name: BLEU type: bleu value: 51.8 - name: chr-F type: chrf value: 0.72558 - task: name: Translation afr-fra type: translation args: afr-fra dataset: name: ntrex128 type: ntrex128 args: afr-fra metrics: - name: BLEU type: bleu value: 29.3 - name: chr-F type: chrf value: 0.56601 - task: name: Translation afr-por type: translation args: afr-por dataset: name: ntrex128 type: ntrex128 args: afr-por metrics: - name: BLEU type: bleu value: 28.1 - name: chr-F type: chrf value: 0.55396 - task: name: Translation afr-spa type: translation args: afr-spa dataset: name: ntrex128 type: ntrex128 args: afr-spa metrics: - name: BLEU type: bleu value: 33.7 - name: chr-F type: chrf value: 0.58558 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: ntrex128 type: ntrex128 args: deu-eng metrics: - name: BLEU type: bleu value: 33.8 - name: chr-F type: chrf value: 0.61722 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: ntrex128 type: ntrex128 args: deu-fra metrics: - name: BLEU type: bleu value: 28.6 - name: chr-F type: chrf value: 0.55908 - task: name: Translation deu-por type: translation args: deu-por dataset: name: ntrex128 type: ntrex128 args: deu-por metrics: - name: BLEU type: bleu value: 25.7 - name: chr-F type: chrf value: 0.54059 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: ntrex128 type: ntrex128 args: deu-spa metrics: - name: BLEU type: bleu value: 30.8 - name: chr-F type: chrf value: 0.56887 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: ntrex128 type: ntrex128 args: eng-deu metrics: - name: BLEU type: bleu value: 29.8 - name: chr-F type: chrf value: 0.58492 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: ntrex128 type: ntrex128 args: eng-fra metrics: - name: BLEU type: bleu value: 35.2 - name: chr-F type: chrf value: 0.61349 - task: name: Translation eng-por type: translation args: eng-por dataset: name: ntrex128 type: ntrex128 args: eng-por metrics: - name: BLEU type: bleu value: 33.4 - name: chr-F type: chrf value: 0.59785 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: ntrex128 type: ntrex128 args: eng-spa metrics: - name: BLEU type: bleu value: 40.1 - name: chr-F type: chrf value: 0.63935 - task: name: Translation ltz-deu type: translation args: ltz-deu dataset: name: ntrex128 type: ntrex128 args: ltz-deu metrics: - name: BLEU type: bleu value: 21.9 - name: chr-F type: chrf value: 0.51469 - task: name: Translation ltz-eng type: translation args: ltz-eng dataset: name: ntrex128 type: ntrex128 args: ltz-eng metrics: - name: BLEU type: bleu value: 32.4 - name: chr-F type: chrf value: 0.58627 - task: name: Translation ltz-fra type: translation args: ltz-fra dataset: name: ntrex128 type: ntrex128 args: ltz-fra metrics: - name: BLEU type: bleu value: 22.8 - name: chr-F type: chrf value: 0.50491 - task: name: Translation ltz-por type: translation args: ltz-por dataset: name: ntrex128 type: ntrex128 args: ltz-por metrics: - name: BLEU type: bleu value: 18.7 - name: chr-F type: chrf value: 0.45364 - task: name: Translation ltz-spa type: translation args: ltz-spa dataset: name: ntrex128 type: ntrex128 args: ltz-spa metrics: - name: BLEU type: bleu value: 21.6 - name: chr-F type: chrf value: 0.47568 - task: name: Translation nld-deu type: translation args: nld-deu dataset: name: ntrex128 type: ntrex128 args: nld-deu metrics: - name: BLEU type: bleu value: 25.7 - name: chr-F type: chrf value: 0.55943 - task: name: Translation nld-eng type: translation args: nld-eng dataset: name: ntrex128 type: ntrex128 args: nld-eng metrics: - name: BLEU type: bleu value: 36.1 - name: chr-F type: chrf value: 0.63470 - task: name: Translation nld-fra type: translation args: nld-fra dataset: name: ntrex128 type: ntrex128 args: nld-fra metrics: - name: BLEU type: bleu value: 27.5 - name: chr-F type: chrf value: 0.55832 - task: name: Translation nld-por type: translation args: nld-por dataset: name: ntrex128 type: ntrex128 args: nld-por metrics: - name: BLEU type: bleu value: 27.3 - name: chr-F type: chrf value: 0.54714 - task: name: Translation nld-spa type: translation args: nld-spa dataset: name: ntrex128 type: ntrex128 args: nld-spa metrics: - name: BLEU type: bleu value: 32.1 - name: chr-F type: chrf value: 0.57692 - task: name: Translation afr-deu type: translation args: afr-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: afr-deu metrics: - name: BLEU type: bleu value: 48.8 - name: chr-F type: chrf value: 0.68492 - task: name: Translation afr-eng type: translation args: afr-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: afr-eng metrics: - name: BLEU type: bleu value: 59.6 - name: chr-F type: chrf value: 0.72943 - task: name: Translation afr-spa type: translation args: afr-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: afr-spa metrics: - name: BLEU type: bleu value: 58.4 - name: chr-F type: chrf value: 0.72793 - task: name: Translation deu-deu type: translation args: deu-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-deu metrics: - name: BLEU type: bleu value: 34.8 - name: chr-F type: chrf value: 0.59840 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-eng metrics: - name: BLEU type: bleu value: 48.5 - name: chr-F type: chrf value: 0.65957 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-fra metrics: - name: BLEU type: bleu value: 50.2 - name: chr-F type: chrf value: 0.68054 - task: name: Translation deu-por type: translation args: deu-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-por metrics: - name: BLEU type: bleu value: 42.8 - name: chr-F type: chrf value: 0.63368 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-spa metrics: - name: BLEU type: bleu value: 49.3 - name: chr-F type: chrf value: 0.68198 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-deu metrics: - name: BLEU type: bleu value: 40.5 - name: chr-F type: chrf value: 0.62497 - task: name: Translation eng-eng type: translation args: eng-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-eng metrics: - name: BLEU type: bleu value: 57.3 - name: chr-F type: chrf value: 0.79878 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-fra metrics: - name: BLEU type: bleu value: 50.9 - name: chr-F type: chrf value: 0.68567 - task: name: Translation eng-por type: translation args: eng-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-por metrics: - name: BLEU type: bleu value: 53.4 - name: chr-F type: chrf value: 0.72204 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-spa metrics: - name: BLEU type: bleu value: 55.3 - name: chr-F type: chrf value: 0.72539 - task: name: Translation fry-eng type: translation args: fry-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fry-eng metrics: - name: BLEU type: bleu value: 37.0 - name: chr-F type: chrf value: 0.55137 - task: name: Translation gos-deu type: translation args: gos-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: gos-deu metrics: - name: BLEU type: bleu value: 24.7 - name: chr-F type: chrf value: 0.46120 - task: name: Translation gos-eng type: translation args: gos-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: gos-eng metrics: - name: BLEU type: bleu value: 22.3 - name: chr-F type: chrf value: 0.38628 - task: name: Translation gsw-eng type: translation args: gsw-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: gsw-eng metrics: - name: BLEU type: bleu value: 27.5 - name: chr-F type: chrf value: 0.43003 - task: name: Translation ltz-deu type: translation args: ltz-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: ltz-deu metrics: - name: BLEU type: bleu value: 32.0 - name: chr-F type: chrf value: 0.48474 - task: name: Translation ltz-eng type: translation args: ltz-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: ltz-eng metrics: - name: BLEU type: bleu value: 56.4 - name: chr-F type: chrf value: 0.65366 - task: name: Translation multi-multi type: translation args: multi-multi dataset: name: tatoeba-test-v2020-07-28-v2023-09-26 type: tatoeba_mt args: multi-multi metrics: - name: BLEU type: bleu value: 50.3 - name: chr-F type: chrf value: 0.68713 - task: name: Translation nds-deu type: translation args: nds-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nds-deu metrics: - name: BLEU type: bleu value: 45.9 - name: chr-F type: chrf value: 0.65251 - task: name: Translation nds-eng type: translation args: nds-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nds-eng metrics: - name: BLEU type: bleu value: 44.7 - name: chr-F type: chrf value: 0.61858 - task: name: Translation nds-fra type: translation args: nds-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nds-fra metrics: - name: BLEU type: bleu value: 43.9 - name: chr-F type: chrf value: 0.60412 - task: name: Translation nds-por type: translation args: nds-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nds-por metrics: - name: BLEU type: bleu value: 39.5 - name: chr-F type: chrf value: 0.58778 - task: name: Translation nds-spa type: translation args: nds-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nds-spa metrics: - name: BLEU type: bleu value: 43.9 - name: chr-F type: chrf value: 0.63404 - task: name: Translation nld-deu type: translation args: nld-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nld-deu metrics: - name: BLEU type: bleu value: 55.7 - name: chr-F type: chrf value: 0.72998 - task: name: Translation nld-eng type: translation args: nld-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nld-eng metrics: - name: BLEU type: bleu value: 60.9 - name: chr-F type: chrf value: 0.74362 - task: name: Translation nld-fra type: translation args: nld-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nld-fra metrics: - name: BLEU type: bleu value: 48.0 - name: chr-F type: chrf value: 0.68461 - task: name: Translation nld-por type: translation args: nld-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nld-por metrics: - name: BLEU type: bleu value: 49.3 - name: chr-F type: chrf value: 0.68798 - task: name: Translation nld-spa type: translation args: nld-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: nld-spa metrics: - name: BLEU type: bleu value: 51.6 - name: chr-F type: chrf value: 0.69971 - task: name: Translation yid-eng type: translation args: yid-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: yid-eng metrics: - name: BLEU type: bleu value: 31.5 - name: chr-F type: chrf value: 0.49807 - task: name: Translation yid-fra type: translation args: yid-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: yid-fra metrics: - name: BLEU type: bleu value: 31.9 - name: chr-F type: chrf value: 0.54147 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: tico19-test type: tico19-test args: eng-fra metrics: - name: BLEU type: bleu value: 39.5 - name: chr-F type: chrf value: 0.62559 - task: name: Translation eng-por type: translation args: eng-por dataset: name: tico19-test type: tico19-test args: eng-por metrics: - name: BLEU type: bleu value: 49.8 - name: chr-F type: chrf value: 0.72765 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: tico19-test type: tico19-test args: eng-spa metrics: - name: BLEU type: bleu value: 51.6 - name: chr-F type: chrf value: 0.72905 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2008 type: wmt-2008-news args: deu-eng metrics: - name: BLEU type: bleu value: 27.0 - name: chr-F type: chrf value: 0.54434 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2008 type: wmt-2008-news args: deu-fra metrics: - name: BLEU type: bleu value: 26.2 - name: chr-F type: chrf value: 0.55076 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: newstest2008 type: wmt-2008-news args: deu-spa metrics: - name: BLEU type: bleu value: 25.6 - name: chr-F type: chrf value: 0.54056 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2008 type: wmt-2008-news args: eng-deu metrics: - name: BLEU type: bleu value: 23.0 - name: chr-F type: chrf value: 0.52906 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2008 type: wmt-2008-news args: eng-fra metrics: - name: BLEU type: bleu value: 26.8 - name: chr-F type: chrf value: 0.55247 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: newstest2008 type: wmt-2008-news args: eng-spa metrics: - name: BLEU type: bleu value: 29.6 - name: chr-F type: chrf value: 0.56423 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2009 type: wmt-2009-news args: deu-eng metrics: - name: BLEU type: bleu value: 26.7 - name: chr-F type: chrf value: 0.53972 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2009 type: wmt-2009-news args: deu-fra metrics: - name: BLEU type: bleu value: 25.6 - name: chr-F type: chrf value: 0.53975 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: newstest2009 type: wmt-2009-news args: deu-spa metrics: - name: BLEU type: bleu value: 25.6 - name: chr-F type: chrf value: 0.53677 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2009 type: wmt-2009-news args: eng-deu metrics: - name: BLEU type: bleu value: 22.1 - name: chr-F type: chrf value: 0.53097 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2009 type: wmt-2009-news args: eng-fra metrics: - name: BLEU type: bleu value: 29.1 - name: chr-F type: chrf value: 0.57542 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: newstest2009 type: wmt-2009-news args: eng-spa metrics: - name: BLEU type: bleu value: 29.8 - name: chr-F type: chrf value: 0.57733 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2010 type: wmt-2010-news args: deu-eng metrics: - name: BLEU type: bleu value: 30.2 - name: chr-F type: chrf value: 0.58278 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2010 type: wmt-2010-news args: deu-fra metrics: - name: BLEU type: bleu value: 29.0 - name: chr-F type: chrf value: 0.57876 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: newstest2010 type: wmt-2010-news args: deu-spa metrics: - name: BLEU type: bleu value: 32.6 - name: chr-F type: chrf value: 0.59402 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2010 type: wmt-2010-news args: eng-deu metrics: - name: BLEU type: bleu value: 25.3 - name: chr-F type: chrf value: 0.54587 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2010 type: wmt-2010-news args: eng-fra metrics: - name: BLEU type: bleu value: 32.0 - name: chr-F type: chrf value: 0.59460 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: newstest2010 type: wmt-2010-news args: eng-spa metrics: - name: BLEU type: bleu value: 36.3 - name: chr-F type: chrf value: 0.61861 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2011 type: wmt-2011-news args: deu-eng metrics: - name: BLEU type: bleu value: 26.8 - name: chr-F type: chrf value: 0.55074 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2011 type: wmt-2011-news args: deu-fra metrics: - name: BLEU type: bleu value: 27.4 - name: chr-F type: chrf value: 0.55879 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: newstest2011 type: wmt-2011-news args: deu-spa metrics: - name: BLEU type: bleu value: 30.2 - name: chr-F type: chrf value: 0.56593 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2011 type: wmt-2011-news args: eng-deu metrics: - name: BLEU type: bleu value: 22.7 - name: chr-F type: chrf value: 0.52619 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2011 type: wmt-2011-news args: eng-fra metrics: - name: BLEU type: bleu value: 34.1 - name: chr-F type: chrf value: 0.60960 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: newstest2011 type: wmt-2011-news args: eng-spa metrics: - name: BLEU type: bleu value: 38.5 - name: chr-F type: chrf value: 0.62056 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2012 type: wmt-2012-news args: deu-eng metrics: - name: BLEU type: bleu value: 28.4 - name: chr-F type: chrf value: 0.56290 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2012 type: wmt-2012-news args: deu-fra metrics: - name: BLEU type: bleu value: 27.3 - name: chr-F type: chrf value: 0.55931 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: newstest2012 type: wmt-2012-news args: deu-spa metrics: - name: BLEU type: bleu value: 31.5 - name: chr-F type: chrf value: 0.57369 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2012 type: wmt-2012-news args: eng-deu metrics: - name: BLEU type: bleu value: 23.3 - name: chr-F type: chrf value: 0.52668 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2012 type: wmt-2012-news args: eng-fra metrics: - name: BLEU type: bleu value: 31.6 - name: chr-F type: chrf value: 0.59076 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: newstest2012 type: wmt-2012-news args: eng-spa metrics: - name: BLEU type: bleu value: 38.8 - name: chr-F type: chrf value: 0.62361 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2013 type: wmt-2013-news args: deu-eng metrics: - name: BLEU type: bleu value: 31.8 - name: chr-F type: chrf value: 0.58065 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2013 type: wmt-2013-news args: deu-fra metrics: - name: BLEU type: bleu value: 30.0 - name: chr-F type: chrf value: 0.56431 - task: name: Translation deu-spa type: translation args: deu-spa dataset: name: newstest2013 type: wmt-2013-news args: deu-spa metrics: - name: BLEU type: bleu value: 31.5 - name: chr-F type: chrf value: 0.56965 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2013 type: wmt-2013-news args: eng-deu metrics: - name: BLEU type: bleu value: 26.9 - name: chr-F type: chrf value: 0.55423 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2013 type: wmt-2013-news args: eng-fra metrics: - name: BLEU type: bleu value: 33.1 - name: chr-F type: chrf value: 0.58760 - task: name: Translation eng-spa type: translation args: eng-spa dataset: name: newstest2013 type: wmt-2013-news args: eng-spa metrics: - name: BLEU type: bleu value: 35.1 - name: chr-F type: chrf value: 0.59825 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2014 type: wmt-2014-news args: deu-eng metrics: - name: BLEU type: bleu value: 32.9 - name: chr-F type: chrf value: 0.59617 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2014 type: wmt-2014-news args: eng-deu metrics: - name: BLEU type: bleu value: 28.0 - name: chr-F type: chrf value: 0.58847 - task: name: Translation eng-fra type: translation args: eng-fra dataset: name: newstest2014 type: wmt-2014-news args: eng-fra metrics: - name: BLEU type: bleu value: 39.9 - name: chr-F type: chrf value: 0.65294 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2015 type: wmt-2015-news args: deu-eng metrics: - name: BLEU type: bleu value: 33.8 - name: chr-F type: chrf value: 0.59741 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2015 type: wmt-2015-news args: eng-deu metrics: - name: BLEU type: bleu value: 31.0 - name: chr-F type: chrf value: 0.59474 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2016 type: wmt-2016-news args: deu-eng metrics: - name: BLEU type: bleu value: 40.6 - name: chr-F type: chrf value: 0.64981 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2016 type: wmt-2016-news args: eng-deu metrics: - name: BLEU type: bleu value: 37.1 - name: chr-F type: chrf value: 0.63839 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2017 type: wmt-2017-news args: deu-eng metrics: - name: BLEU type: bleu value: 35.5 - name: chr-F type: chrf value: 0.60957 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2017 type: wmt-2017-news args: eng-deu metrics: - name: BLEU type: bleu value: 30.0 - name: chr-F type: chrf value: 0.58967 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2018 type: wmt-2018-news args: deu-eng metrics: - name: BLEU type: bleu value: 43.4 - name: chr-F type: chrf value: 0.66739 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2018 type: wmt-2018-news args: eng-deu metrics: - name: BLEU type: bleu value: 44.9 - name: chr-F type: chrf value: 0.68858 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2019 type: wmt-2019-news args: deu-eng metrics: - name: BLEU type: bleu value: 39.6 - name: chr-F type: chrf value: 0.63671 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2019 type: wmt-2019-news args: deu-fra metrics: - name: BLEU type: bleu value: 36.1 - name: chr-F type: chrf value: 0.63043 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2019 type: wmt-2019-news args: eng-deu metrics: - name: BLEU type: bleu value: 41.4 - name: chr-F type: chrf value: 0.65934 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2020 type: wmt-2020-news args: deu-eng metrics: - name: BLEU type: bleu value: 34.5 - name: chr-F type: chrf value: 0.60800 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2020 type: wmt-2020-news args: deu-fra metrics: - name: BLEU type: bleu value: 33.1 - name: chr-F type: chrf value: 0.60544 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2020 type: wmt-2020-news args: eng-deu metrics: - name: BLEU type: bleu value: 31.7 - name: chr-F type: chrf value: 0.60078 - task: name: Translation deu-eng type: translation args: deu-eng dataset: name: newstest2021 type: wmt-2021-news args: deu-eng metrics: - name: BLEU type: bleu value: 31.9 - name: chr-F type: chrf value: 0.60048 - task: name: Translation deu-fra type: translation args: deu-fra dataset: name: newstest2021 type: wmt-2021-news args: deu-fra metrics: - name: BLEU type: bleu value: 31.8 - name: chr-F type: chrf value: 0.59590 - task: name: Translation eng-deu type: translation args: eng-deu dataset: name: newstest2021 type: wmt-2021-news args: eng-deu metrics: - name: BLEU type: bleu value: 25.6 - name: chr-F type: chrf value: 0.56133 --- # opus-mt-tc-bible-big-gmw-deu_eng_fra_por_spa ## Table of Contents - [Model Details](#model-details) - [Uses](#uses) - [Risks, Limitations and Biases](#risks-limitations-and-biases) - [How to Get Started With the Model](#how-to-get-started-with-the-model) - [Training](#training) - [Evaluation](#evaluation) - [Citation Information](#citation-information) - [Acknowledgements](#acknowledgements) ## Model Details Neural machine translation model for translating from West Germanic languages (gmw) to unknown (deu+eng+fra+por+spa). This model is part of the [OPUS-MT project](https://github.com/Helsinki-NLP/Opus-MT), an effort to make neural machine translation models widely available and accessible for many languages in the world. All models are originally trained using the amazing framework of [Marian NMT](https://marian-nmt.github.io/), an efficient NMT implementation written in pure C++. The models have been converted to pyTorch using the transformers library by huggingface. Training data is taken from [OPUS](https://opus.nlpl.eu/) and training pipelines use the procedures of [OPUS-MT-train](https://github.com/Helsinki-NLP/Opus-MT-train). **Model Description:** - **Developed by:** Language Technology Research Group at the University of Helsinki - **Model Type:** Translation (transformer-big) - **Release**: 2024-05-30 - **License:** Apache-2.0 - **Language(s):** - Source Language(s): afr ang bar bis bzj deu djk drt eng enm frr fry gos gsw hrx hwc icr jam kri ksh lim ltz nds nld ofs pcm pdc pfl pih pis rop sco srm srn stq swg tcs tpi vls wae yid zea - Target Language(s): deu eng fra por spa - Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<< - **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip) - **Resources for more information:** - [OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/gmw-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30) - [OPUS-MT-train GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train) - [More information about MarianNMT models in the transformers library](https://huggingface.co./docs/transformers/model_doc/marian) - [Tatoeba Translation Challenge](https://github.com/Helsinki-NLP/Tatoeba-Challenge/) - [HPLT bilingual data v1 (as part of the Tatoeba Translation Challenge dataset)](https://hplt-project.org/datasets/v1) - [A massively parallel Bible corpus](https://aclanthology.org/L14-1215/) This is a multilingual translation model with multiple target languages. A sentence initial language token is required in the form of `>>id<<` (id = valid target language ID), e.g. `>>deu<<` ## Uses This model can be used for translation and text-to-text generation. ## Risks, Limitations and Biases **CONTENT WARNING: Readers should be aware that the model is trained on various public data sets that may contain content that is disturbing, offensive, and can propagate historical and current stereotypes.** Significant research has explored bias and fairness issues with language models (see, e.g., [Sheng et al. (2021)](https://aclanthology.org/2021.acl-long.330.pdf) and [Bender et al. (2021)](https://dl.acm.org/doi/pdf/10.1145/3442188.3445922)). ## How to Get Started With the Model A short example code: ```python from transformers import MarianMTModel, MarianTokenizer src_text = [ ">>deu<< Replace this with text in an accepted source language.", ">>spa<< This is the second sentence." ] model_name = "pytorch-models/opus-mt-tc-bible-big-gmw-deu_eng_fra_por_spa" tokenizer = MarianTokenizer.from_pretrained(model_name) model = MarianMTModel.from_pretrained(model_name) translated = model.generate(**tokenizer(src_text, return_tensors="pt", padding=True)) for t in translated: print( tokenizer.decode(t, skip_special_tokens=True) ) ``` You can also use OPUS-MT models with the transformers pipelines, for example: ```python from transformers import pipeline pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-gmw-deu_eng_fra_por_spa") print(pipe(">>deu<< Replace this with text in an accepted source language.")) ``` ## Training - **Data**: opusTCv20230926max50+bt+jhubc ([source](https://github.com/Helsinki-NLP/Tatoeba-Challenge)) - **Pre-processing**: SentencePiece (spm32k,spm32k) - **Model Type:** transformer-big - **Original MarianNMT Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip) - **Training Scripts**: [GitHub Repo](https://github.com/Helsinki-NLP/OPUS-MT-train) ## Evaluation * [Model scores at the OPUS-MT dashboard](https://opus.nlpl.eu/dashboard/index.php?pkg=opusmt&test=all&scoreslang=all&chart=standard&model=Tatoeba-MT-models/gmw-deu%2Beng%2Bfra%2Bpor%2Bspa/opusTCv20230926max50%2Bbt%2Bjhubc_transformer-big_2024-05-30) * test set translations: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt) * test set scores: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt](https://object.pouta.csc.fi/Tatoeba-MT-models/gmw-deu+eng+fra+por+spa/opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt) * benchmark results: [benchmark_results.txt](benchmark_results.txt) * benchmark output: [benchmark_translations.zip](benchmark_translations.zip) | langpair | testset | chr-F | BLEU | #sent | #words | |----------|---------|-------|-------|-------|--------| | afr-deu | tatoeba-test-v2021-08-07 | 0.68492 | 48.8 | 1583 | 9105 | | afr-eng | tatoeba-test-v2021-08-07 | 0.72943 | 59.6 | 1374 | 9622 | | afr-spa | tatoeba-test-v2021-08-07 | 0.72793 | 58.4 | 448 | 2783 | | deu-deu | tatoeba-test-v2021-08-07 | 0.59840 | 34.8 | 2500 | 20806 | | deu-eng | tatoeba-test-v2021-08-07 | 0.65957 | 48.5 | 17565 | 149462 | | deu-fra | tatoeba-test-v2021-08-07 | 0.68054 | 50.2 | 12418 | 102721 | | deu-por | tatoeba-test-v2021-08-07 | 0.63368 | 42.8 | 10000 | 81482 | | deu-spa | tatoeba-test-v2021-08-07 | 0.68198 | 49.3 | 10521 | 82570 | | eng-deu | tatoeba-test-v2021-08-07 | 0.62497 | 40.5 | 17565 | 151568 | | eng-eng | tatoeba-test-v2021-08-07 | 0.79878 | 57.3 | 12062 | 115106 | | eng-fra | tatoeba-test-v2021-08-07 | 0.68567 | 50.9 | 12681 | 106378 | | eng-por | tatoeba-test-v2021-08-07 | 0.72204 | 53.4 | 13222 | 105265 | | eng-spa | tatoeba-test-v2021-08-07 | 0.72539 | 55.3 | 16583 | 134710 | | fry-eng | tatoeba-test-v2021-08-07 | 0.55137 | 37.0 | 220 | 1573 | | gos-deu | tatoeba-test-v2021-08-07 | 0.46120 | 24.7 | 207 | 1168 | | gos-eng | tatoeba-test-v2021-08-07 | 0.38628 | 22.3 | 1154 | 5635 | | gsw-eng | tatoeba-test-v2021-08-07 | 0.43003 | 27.5 | 205 | 990 | | ltz-deu | tatoeba-test-v2021-08-07 | 0.48474 | 32.0 | 347 | 2208 | | ltz-eng | tatoeba-test-v2021-08-07 | 0.65366 | 56.4 | 293 | 1840 | | nds-deu | tatoeba-test-v2021-08-07 | 0.65251 | 45.9 | 9999 | 74564 | | nds-eng | tatoeba-test-v2021-08-07 | 0.61858 | 44.7 | 2500 | 17589 | | nds-fra | tatoeba-test-v2021-08-07 | 0.60412 | 43.9 | 857 | 5676 | | nds-por | tatoeba-test-v2021-08-07 | 0.58778 | 39.5 | 207 | 1256 | | nds-spa | tatoeba-test-v2021-08-07 | 0.63404 | 43.9 | 923 | 5540 | | nld-deu | tatoeba-test-v2021-08-07 | 0.72998 | 55.7 | 10218 | 74131 | | nld-eng | tatoeba-test-v2021-08-07 | 0.74362 | 60.9 | 12696 | 89978 | | nld-fra | tatoeba-test-v2021-08-07 | 0.68461 | 48.0 | 11548 | 82974 | | nld-por | tatoeba-test-v2021-08-07 | 0.68798 | 49.3 | 2500 | 17326 | | nld-spa | tatoeba-test-v2021-08-07 | 0.69971 | 51.6 | 10113 | 74981 | | yid-eng | tatoeba-test-v2021-08-07 | 0.49807 | 31.5 | 2483 | 15452 | | yid-fra | tatoeba-test-v2021-08-07 | 0.54147 | 31.9 | 384 | 2455 | | afr-deu | flores101-devtest | 0.57831 | 28.4 | 1012 | 25094 | | afr-eng | flores101-devtest | 0.74272 | 53.8 | 1012 | 24721 | | afr-fra | flores101-devtest | 0.61936 | 36.4 | 1012 | 28343 | | afr-por | flores101-devtest | 0.61309 | 35.4 | 1012 | 26519 | | afr-spa | flores101-devtest | 0.51393 | 22.9 | 1012 | 29199 | | deu-spa | flores101-devtest | 0.52438 | 23.9 | 1012 | 29199 | | eng-deu | flores101-devtest | 0.64236 | 37.2 | 1012 | 25094 | | eng-spa | flores101-devtest | 0.55524 | 27.1 | 1012 | 29199 | | nld-deu | flores101-devtest | 0.53435 | 22.1 | 1012 | 25094 | | nld-eng | flores101-devtest | 0.58686 | 30.0 | 1012 | 24721 | | nld-fra | flores101-devtest | 0.56292 | 28.2 | 1012 | 28343 | | afr-deu | flores200-devtest | 0.58456 | 29.5 | 1012 | 25094 | | afr-eng | flores200-devtest | 0.74857 | 54.7 | 1012 | 24721 | | afr-fra | flores200-devtest | 0.62537 | 37.2 | 1012 | 28343 | | afr-por | flores200-devtest | 0.61751 | 36.1 | 1012 | 26519 | | afr-spa | flores200-devtest | 0.51647 | 23.2 | 1012 | 29199 | | deu-eng | flores200-devtest | 0.67103 | 41.4 | 1012 | 24721 | | deu-fra | flores200-devtest | 0.62658 | 36.8 | 1012 | 28343 | | deu-por | flores200-devtest | 0.60909 | 34.8 | 1012 | 26519 | | deu-spa | flores200-devtest | 0.52584 | 24.2 | 1012 | 29199 | | eng-deu | flores200-devtest | 0.64560 | 37.5 | 1012 | 25094 | | eng-fra | flores200-devtest | 0.70736 | 49.1 | 1012 | 28343 | | eng-por | flores200-devtest | 0.71065 | 49.5 | 1012 | 26519 | | eng-spa | flores200-devtest | 0.55738 | 27.4 | 1012 | 29199 | | lim-deu | flores200-devtest | 0.45062 | 16.1 | 1012 | 25094 | | lim-eng | flores200-devtest | 0.48217 | 21.8 | 1012 | 24721 | | lim-fra | flores200-devtest | 0.44347 | 18.5 | 1012 | 28343 | | lim-por | flores200-devtest | 0.42527 | 16.8 | 1012 | 26519 | | ltz-deu | flores200-devtest | 0.60114 | 31.3 | 1012 | 25094 | | ltz-eng | flores200-devtest | 0.64345 | 39.3 | 1012 | 24721 | | ltz-fra | flores200-devtest | 0.59368 | 33.8 | 1012 | 28343 | | ltz-por | flores200-devtest | 0.51545 | 24.8 | 1012 | 26519 | | ltz-spa | flores200-devtest | 0.44821 | 17.5 | 1012 | 29199 | | nld-deu | flores200-devtest | 0.53650 | 22.4 | 1012 | 25094 | | nld-eng | flores200-devtest | 0.59102 | 30.6 | 1012 | 24721 | | nld-fra | flores200-devtest | 0.56608 | 28.7 | 1012 | 28343 | | nld-por | flores200-devtest | 0.54728 | 26.7 | 1012 | 26519 | | nld-spa | flores200-devtest | 0.49175 | 20.1 | 1012 | 29199 | | tpi-deu | flores200-devtest | 0.40350 | 10.9 | 1012 | 25094 | | tpi-eng | flores200-devtest | 0.48289 | 19.6 | 1012 | 24721 | | tpi-fra | flores200-devtest | 0.43428 | 16.1 | 1012 | 28343 | | tpi-por | flores200-devtest | 0.42966 | 15.4 | 1012 | 26519 | | deu-eng | generaltest2022 | 0.56042 | 31.0 | 1984 | 37634 | | deu-fra | generaltest2022 | 0.61145 | 37.6 | 1984 | 38276 | | eng-deu | generaltest2022 | 0.60090 | 32.5 | 2037 | 38914 | | deu-eng | multi30k_test_2016_flickr | 0.60974 | 40.1 | 1000 | 12955 | | deu-fra | multi30k_test_2016_flickr | 0.62493 | 38.8 | 1000 | 13505 | | eng-deu | multi30k_test_2016_flickr | 0.64164 | 35.3 | 1000 | 12106 | | eng-fra | multi30k_test_2016_flickr | 0.71137 | 50.7 | 1000 | 13505 | | deu-eng | multi30k_test_2017_flickr | 0.63118 | 40.6 | 1000 | 11374 | | deu-fra | multi30k_test_2017_flickr | 0.62614 | 37.0 | 1000 | 12118 | | eng-deu | multi30k_test_2017_flickr | 0.62518 | 33.4 | 1000 | 10755 | | eng-fra | multi30k_test_2017_flickr | 0.71402 | 50.3 | 1000 | 12118 | | deu-eng | multi30k_test_2017_mscoco | 0.55495 | 32.1 | 461 | 5231 | | deu-fra | multi30k_test_2017_mscoco | 0.59307 | 34.7 | 461 | 5484 | | eng-deu | multi30k_test_2017_mscoco | 0.58028 | 29.7 | 461 | 5158 | | eng-fra | multi30k_test_2017_mscoco | 0.73637 | 54.7 | 461 | 5484 | | deu-eng | multi30k_test_2018_flickr | 0.59367 | 36.7 | 1071 | 14689 | | deu-fra | multi30k_test_2018_flickr | 0.57388 | 31.3 | 1071 | 15867 | | eng-deu | multi30k_test_2018_flickr | 0.59998 | 30.8 | 1071 | 13703 | | eng-fra | multi30k_test_2018_flickr | 0.65354 | 41.6 | 1071 | 15867 | | eng-fra | newsdiscusstest2015 | 0.63308 | 37.7 | 1500 | 27975 | | deu-eng | newssyscomb2009 | 0.55170 | 28.3 | 502 | 11818 | | deu-fra | newssyscomb2009 | 0.56021 | 27.4 | 502 | 12331 | | deu-spa | newssyscomb2009 | 0.55546 | 28.1 | 502 | 12503 | | eng-deu | newssyscomb2009 | 0.53919 | 23.0 | 502 | 11271 | | eng-fra | newssyscomb2009 | 0.58384 | 29.5 | 502 | 12331 | | eng-spa | newssyscomb2009 | 0.58266 | 31.0 | 502 | 12503 | | deu-eng | newstest2008 | 0.54434 | 27.0 | 2051 | 49380 | | deu-fra | newstest2008 | 0.55076 | 26.2 | 2051 | 52685 | | deu-spa | newstest2008 | 0.54056 | 25.6 | 2051 | 52586 | | eng-deu | newstest2008 | 0.52906 | 23.0 | 2051 | 47447 | | eng-fra | newstest2008 | 0.55247 | 26.8 | 2051 | 52685 | | eng-spa | newstest2008 | 0.56423 | 29.6 | 2051 | 52586 | | deu-eng | newstest2009 | 0.53972 | 26.7 | 2525 | 65399 | | deu-fra | newstest2009 | 0.53975 | 25.6 | 2525 | 69263 | | deu-spa | newstest2009 | 0.53677 | 25.6 | 2525 | 68111 | | eng-deu | newstest2009 | 0.53097 | 22.1 | 2525 | 62816 | | eng-fra | newstest2009 | 0.57542 | 29.1 | 2525 | 69263 | | eng-spa | newstest2009 | 0.57733 | 29.8 | 2525 | 68111 | | deu-eng | newstest2010 | 0.58278 | 30.2 | 2489 | 61711 | | deu-fra | newstest2010 | 0.57876 | 29.0 | 2489 | 66022 | | deu-spa | newstest2010 | 0.59402 | 32.6 | 2489 | 65480 | | eng-deu | newstest2010 | 0.54587 | 25.3 | 2489 | 61503 | | eng-fra | newstest2010 | 0.59460 | 32.0 | 2489 | 66022 | | eng-spa | newstest2010 | 0.61861 | 36.3 | 2489 | 65480 | | deu-eng | newstest2011 | 0.55074 | 26.8 | 3003 | 74681 | | deu-fra | newstest2011 | 0.55879 | 27.4 | 3003 | 80626 | | deu-spa | newstest2011 | 0.56593 | 30.2 | 3003 | 79476 | | eng-deu | newstest2011 | 0.52619 | 22.7 | 3003 | 72981 | | eng-fra | newstest2011 | 0.60960 | 34.1 | 3003 | 80626 | | eng-spa | newstest2011 | 0.62056 | 38.5 | 3003 | 79476 | | deu-eng | newstest2012 | 0.56290 | 28.4 | 3003 | 72812 | | deu-fra | newstest2012 | 0.55931 | 27.3 | 3003 | 78011 | | deu-spa | newstest2012 | 0.57369 | 31.5 | 3003 | 79006 | | eng-deu | newstest2012 | 0.52668 | 23.3 | 3003 | 72886 | | eng-fra | newstest2012 | 0.59076 | 31.6 | 3003 | 78011 | | eng-spa | newstest2012 | 0.62361 | 38.8 | 3003 | 79006 | | deu-eng | newstest2013 | 0.58065 | 31.8 | 3000 | 64505 | | deu-fra | newstest2013 | 0.56431 | 30.0 | 3000 | 70037 | | deu-spa | newstest2013 | 0.56965 | 31.5 | 3000 | 70528 | | eng-deu | newstest2013 | 0.55423 | 26.9 | 3000 | 63737 | | eng-fra | newstest2013 | 0.58760 | 33.1 | 3000 | 70037 | | eng-spa | newstest2013 | 0.59825 | 35.1 | 3000 | 70528 | | deu-eng | newstest2014 | 0.59617 | 32.9 | 3003 | 67337 | | eng-deu | newstest2014 | 0.58847 | 28.0 | 3003 | 62688 | | eng-fra | newstest2014 | 0.65294 | 39.9 | 3003 | 77306 | | deu-eng | newstest2015 | 0.59741 | 33.8 | 2169 | 46443 | | eng-deu | newstest2015 | 0.59474 | 31.0 | 2169 | 44260 | | deu-eng | newstest2016 | 0.64981 | 40.6 | 2999 | 64119 | | eng-deu | newstest2016 | 0.63839 | 37.1 | 2999 | 62669 | | deu-eng | newstest2017 | 0.60957 | 35.5 | 3004 | 64399 | | eng-deu | newstest2017 | 0.58967 | 30.0 | 3004 | 61287 | | deu-eng | newstest2018 | 0.66739 | 43.4 | 2998 | 67012 | | eng-deu | newstest2018 | 0.68858 | 44.9 | 2998 | 64276 | | deu-eng | newstest2019 | 0.63671 | 39.6 | 2000 | 39227 | | deu-fra | newstest2019 | 0.63043 | 36.1 | 1701 | 42509 | | eng-deu | newstest2019 | 0.65934 | 41.4 | 1997 | 48746 | | deu-eng | newstest2020 | 0.60800 | 34.5 | 785 | 38220 | | deu-fra | newstest2020 | 0.60544 | 33.1 | 1619 | 36890 | | eng-deu | newstest2020 | 0.60078 | 31.7 | 1418 | 52383 | | deu-eng | newstest2021 | 0.60048 | 31.9 | 1000 | 20180 | | deu-fra | newstest2021 | 0.59590 | 31.8 | 1000 | 23757 | | eng-deu | newstest2021 | 0.56133 | 25.6 | 1002 | 27970 | | deu-eng | newstestALL2020 | 0.60800 | 34.5 | 785 | 38220 | | eng-deu | newstestALL2020 | 0.60078 | 31.7 | 1418 | 52383 | | deu-eng | newstestB2020 | 0.60795 | 34.4 | 785 | 37696 | | eng-deu | newstestB2020 | 0.59256 | 31.5 | 1418 | 53092 | | afr-deu | ntrex128 | 0.55289 | 25.8 | 1997 | 48761 | | afr-eng | ntrex128 | 0.72558 | 51.8 | 1997 | 47673 | | afr-fra | ntrex128 | 0.56601 | 29.3 | 1997 | 53481 | | afr-por | ntrex128 | 0.55396 | 28.1 | 1997 | 51631 | | afr-spa | ntrex128 | 0.58558 | 33.7 | 1997 | 54107 | | deu-eng | ntrex128 | 0.61722 | 33.8 | 1997 | 47673 | | deu-fra | ntrex128 | 0.55908 | 28.6 | 1997 | 53481 | | deu-por | ntrex128 | 0.54059 | 25.7 | 1997 | 51631 | | deu-spa | ntrex128 | 0.56887 | 30.8 | 1997 | 54107 | | eng-deu | ntrex128 | 0.58492 | 29.8 | 1997 | 48761 | | eng-fra | ntrex128 | 0.61349 | 35.2 | 1997 | 53481 | | eng-por | ntrex128 | 0.59785 | 33.4 | 1997 | 51631 | | eng-spa | ntrex128 | 0.63935 | 40.1 | 1997 | 54107 | | ltz-deu | ntrex128 | 0.51469 | 21.9 | 1997 | 48761 | | ltz-eng | ntrex128 | 0.58627 | 32.4 | 1997 | 47673 | | ltz-fra | ntrex128 | 0.50491 | 22.8 | 1997 | 53481 | | ltz-por | ntrex128 | 0.45364 | 18.7 | 1997 | 51631 | | ltz-spa | ntrex128 | 0.47568 | 21.6 | 1997 | 54107 | | nld-deu | ntrex128 | 0.55943 | 25.7 | 1997 | 48761 | | nld-eng | ntrex128 | 0.63470 | 36.1 | 1997 | 47673 | | nld-fra | ntrex128 | 0.55832 | 27.5 | 1997 | 53481 | | nld-por | ntrex128 | 0.54714 | 27.3 | 1997 | 51631 | | nld-spa | ntrex128 | 0.57692 | 32.1 | 1997 | 54107 | | eng-fra | tico19-test | 0.62559 | 39.5 | 2100 | 64661 | | eng-por | tico19-test | 0.72765 | 49.8 | 2100 | 62729 | | eng-spa | tico19-test | 0.72905 | 51.6 | 2100 | 66563 | ## Citation Information * Publications: [Democratizing neural machine translation with OPUS-MT](https://doi.org/10.1007/s10579-023-09704-w) and [OPUS-MT – Building open translation services for the World](https://aclanthology.org/2020.eamt-1.61/) and [The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT](https://aclanthology.org/2020.wmt-1.139/) (Please, cite if you use this model.) ```bibtex @article{tiedemann2023democratizing, title={Democratizing neural machine translation with {OPUS-MT}}, author={Tiedemann, J{\"o}rg and Aulamo, Mikko and Bakshandaeva, Daria and Boggia, Michele and Gr{\"o}nroos, Stig-Arne and Nieminen, Tommi and Raganato, Alessandro and Scherrer, Yves and Vazquez, Raul and Virpioja, Sami}, journal={Language Resources and Evaluation}, number={58}, pages={713--755}, year={2023}, publisher={Springer Nature}, issn={1574-0218}, doi={10.1007/s10579-023-09704-w} } @inproceedings{tiedemann-thottingal-2020-opus, title = "{OPUS}-{MT} {--} Building open translation services for the World", author = {Tiedemann, J{\"o}rg and Thottingal, Santhosh}, booktitle = "Proceedings of the 22nd Annual Conference of the European Association for Machine Translation", month = nov, year = "2020", address = "Lisboa, Portugal", publisher = "European Association for Machine Translation", url = "https://aclanthology.org/2020.eamt-1.61", pages = "479--480", } @inproceedings{tiedemann-2020-tatoeba, title = "The Tatoeba Translation Challenge {--} Realistic Data Sets for Low Resource and Multilingual {MT}", author = {Tiedemann, J{\"o}rg}, booktitle = "Proceedings of the Fifth Conference on Machine Translation", month = nov, year = "2020", address = "Online", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2020.wmt-1.139", pages = "1174--1182", } ``` ## Acknowledgements The work is supported by the [HPLT project](https://hplt-project.org/), funded by the European Union’s Horizon Europe research and innovation programme under grant agreement No 101070350. We are also grateful for the generous computational resources and IT infrastructure provided by [CSC -- IT Center for Science](https://www.csc.fi/), Finland, and the [EuroHPC supercomputer LUMI](https://www.lumi-supercomputer.eu/). ## Model conversion info * transformers version: 4.45.1 * OPUS-MT git hash: 0882077 * port time: Tue Oct 8 11:18:52 EEST 2024 * port machine: LM0-400-22516.local