--- library_name: transformers language: - chm - de - en - es - et - fi - fkv - fr - hu - izh - krl - kv - liv - mdf - mrj - myv - pt - se - sma - smn - udm - vep - vot tags: - translation - opus-mt-tc-bible license: apache-2.0 model-index: - name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-fiu results: - task: name: Translation deu-est type: translation args: deu-est dataset: name: flores200-devtest type: flores200-devtest args: deu-est metrics: - name: BLEU type: bleu value: 21.2 - name: chr-F type: chrf value: 0.55333 - task: name: Translation deu-fin type: translation args: deu-fin dataset: name: flores200-devtest type: flores200-devtest args: deu-fin metrics: - name: BLEU type: bleu value: 18.3 - name: chr-F type: chrf value: 0.54020 - task: name: Translation deu-hun type: translation args: deu-hun dataset: name: flores200-devtest type: flores200-devtest args: deu-hun metrics: - name: BLEU type: bleu value: 22.0 - name: chr-F type: chrf value: 0.53579 - task: name: Translation eng-est type: translation args: eng-est dataset: name: flores200-devtest type: flores200-devtest args: eng-est metrics: - name: BLEU type: bleu value: 26.1 - name: chr-F type: chrf value: 0.59496 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: flores200-devtest type: flores200-devtest args: eng-fin metrics: - name: BLEU type: bleu value: 23.1 - name: chr-F type: chrf value: 0.57811 - task: name: Translation eng-hun type: translation args: eng-hun dataset: name: flores200-devtest type: flores200-devtest args: eng-hun metrics: - name: BLEU type: bleu value: 26.7 - name: chr-F type: chrf value: 0.57670 - task: name: Translation fra-est type: translation args: fra-est dataset: name: flores200-devtest type: flores200-devtest args: fra-est metrics: - name: BLEU type: bleu value: 21.2 - name: chr-F type: chrf value: 0.54442 - task: name: Translation fra-fin type: translation args: fra-fin dataset: name: flores200-devtest type: flores200-devtest args: fra-fin metrics: - name: BLEU type: bleu value: 18.5 - name: chr-F type: chrf value: 0.53768 - task: name: Translation fra-hun type: translation args: fra-hun dataset: name: flores200-devtest type: flores200-devtest args: fra-hun metrics: - name: BLEU type: bleu value: 21.2 - name: chr-F type: chrf value: 0.52691 - task: name: Translation por-est type: translation args: por-est dataset: name: flores200-devtest type: flores200-devtest args: por-est metrics: - name: BLEU type: bleu value: 15.6 - name: chr-F type: chrf value: 0.48227 - task: name: Translation por-fin type: translation args: por-fin dataset: name: flores200-devtest type: flores200-devtest args: por-fin metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.53772 - task: name: Translation por-hun type: translation args: por-hun dataset: name: flores200-devtest type: flores200-devtest args: por-hun metrics: - name: BLEU type: bleu value: 21.8 - name: chr-F type: chrf value: 0.53275 - task: name: Translation spa-est type: translation args: spa-est dataset: name: flores200-devtest type: flores200-devtest args: spa-est metrics: - name: BLEU type: bleu value: 15.2 - name: chr-F type: chrf value: 0.50142 - task: name: Translation spa-fin type: translation args: spa-fin dataset: name: flores200-devtest type: flores200-devtest args: spa-fin metrics: - name: BLEU type: bleu value: 13.7 - name: chr-F type: chrf value: 0.50401 - task: name: Translation spa-hun type: translation args: spa-hun dataset: name: flores200-devtest type: flores200-devtest args: spa-hun metrics: - name: BLEU type: bleu value: 16.4 - name: chr-F type: chrf value: 0.49444 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: flores101-devtest type: flores_101 args: eng fin devtest metrics: - name: BLEU type: bleu value: 21.9 - name: chr-F type: chrf value: 0.57265 - task: name: Translation fra-hun type: translation args: fra-hun dataset: name: flores101-devtest type: flores_101 args: fra hun devtest metrics: - name: BLEU type: bleu value: 21.2 - name: chr-F type: chrf value: 0.52691 - task: name: Translation por-fin type: translation args: por-fin dataset: name: flores101-devtest type: flores_101 args: por fin devtest metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.53772 - task: name: Translation por-hun type: translation args: por-hun dataset: name: flores101-devtest type: flores_101 args: por hun devtest metrics: - name: BLEU type: bleu value: 21.8 - name: chr-F type: chrf value: 0.53275 - task: name: Translation spa-est type: translation args: spa-est dataset: name: flores101-devtest type: flores_101 args: spa est devtest metrics: - name: BLEU type: bleu value: 15.2 - name: chr-F type: chrf value: 0.50142 - task: name: Translation spa-fin type: translation args: spa-fin dataset: name: flores101-devtest type: flores_101 args: spa fin devtest metrics: - name: BLEU type: bleu value: 13.7 - name: chr-F type: chrf value: 0.50401 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstestALL2016 type: newstestALL2016 args: eng-fin metrics: - name: BLEU type: bleu value: 24.3 - name: chr-F type: chrf value: 0.57934 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstestALL2017 type: newstestALL2017 args: eng-fin metrics: - name: BLEU type: bleu value: 26.5 - name: chr-F type: chrf value: 0.60204 - task: name: Translation deu-est type: translation args: deu-est dataset: name: ntrex128 type: ntrex128 args: deu-est metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.51761 - task: name: Translation deu-fin type: translation args: deu-fin dataset: name: ntrex128 type: ntrex128 args: deu-fin metrics: - name: BLEU type: bleu value: 15.5 - name: chr-F type: chrf value: 0.50759 - task: name: Translation deu-hun type: translation args: deu-hun dataset: name: ntrex128 type: ntrex128 args: deu-hun metrics: - name: BLEU type: bleu value: 15.6 - name: chr-F type: chrf value: 0.46171 - task: name: Translation eng-est type: translation args: eng-est dataset: name: ntrex128 type: ntrex128 args: eng-est metrics: - name: BLEU type: bleu value: 24.4 - name: chr-F type: chrf value: 0.57099 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: ntrex128 type: ntrex128 args: eng-fin metrics: - name: BLEU type: bleu value: 18.5 - name: chr-F type: chrf value: 0.53413 - task: name: Translation eng-hun type: translation args: eng-hun dataset: name: ntrex128 type: ntrex128 args: eng-hun metrics: - name: BLEU type: bleu value: 16.6 - name: chr-F type: chrf value: 0.47342 - task: name: Translation fra-est type: translation args: fra-est dataset: name: ntrex128 type: ntrex128 args: fra-est metrics: - name: BLEU type: bleu value: 17.7 - name: chr-F type: chrf value: 0.50712 - task: name: Translation fra-fin type: translation args: fra-fin dataset: name: ntrex128 type: ntrex128 args: fra-fin metrics: - name: BLEU type: bleu value: 14.2 - name: chr-F type: chrf value: 0.49215 - task: name: Translation fra-hun type: translation args: fra-hun dataset: name: ntrex128 type: ntrex128 args: fra-hun metrics: - name: BLEU type: bleu value: 14.9 - name: chr-F type: chrf value: 0.44873 - task: name: Translation por-est type: translation args: por-est dataset: name: ntrex128 type: ntrex128 args: por-est metrics: - name: BLEU type: bleu value: 15.1 - name: chr-F type: chrf value: 0.48098 - task: name: Translation por-fin type: translation args: por-fin dataset: name: ntrex128 type: ntrex128 args: por-fin metrics: - name: BLEU type: bleu value: 15.0 - name: chr-F type: chrf value: 0.50875 - task: name: Translation por-hun type: translation args: por-hun dataset: name: ntrex128 type: ntrex128 args: por-hun metrics: - name: BLEU type: bleu value: 15.5 - name: chr-F type: chrf value: 0.45817 - task: name: Translation spa-est type: translation args: spa-est dataset: name: ntrex128 type: ntrex128 args: spa-est metrics: - name: BLEU type: bleu value: 18.5 - name: chr-F type: chrf value: 0.52158 - task: name: Translation spa-fin type: translation args: spa-fin dataset: name: ntrex128 type: ntrex128 args: spa-fin metrics: - name: BLEU type: bleu value: 15.2 - name: chr-F type: chrf value: 0.50947 - task: name: Translation spa-hun type: translation args: spa-hun dataset: name: ntrex128 type: ntrex128 args: spa-hun metrics: - name: BLEU type: bleu value: 16.1 - name: chr-F type: chrf value: 0.46051 - task: name: Translation deu-est type: translation args: deu-est dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-est metrics: - name: BLEU type: bleu value: 57.8 - name: chr-F type: chrf value: 0.76586 - task: name: Translation deu-fin type: translation args: deu-fin dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-fin metrics: - name: BLEU type: bleu value: 40.7 - name: chr-F type: chrf value: 0.64286 - task: name: Translation deu-hun type: translation args: deu-hun dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-hun metrics: - name: BLEU type: bleu value: 31.2 - name: chr-F type: chrf value: 0.57007 - task: name: Translation eng-est type: translation args: eng-est dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-est metrics: - name: BLEU type: bleu value: 50.6 - name: chr-F type: chrf value: 0.69134 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-fin metrics: - name: BLEU type: bleu value: 37.6 - name: chr-F type: chrf value: 0.62482 - task: name: Translation eng-hun type: translation args: eng-hun dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-hun metrics: - name: BLEU type: bleu value: 35.9 - name: chr-F type: chrf value: 0.59750 - task: name: Translation fra-fin type: translation args: fra-fin dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fra-fin metrics: - name: BLEU type: bleu value: 45.0 - name: chr-F type: chrf value: 0.65723 - task: name: Translation fra-hun type: translation args: fra-hun dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fra-hun metrics: - name: BLEU type: bleu value: 40.6 - name: chr-F type: chrf value: 0.63096 - 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: 32.8 - name: chr-F type: chrf value: 0.58505 - task: name: Translation por-fin type: translation args: por-fin dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: por-fin metrics: - name: BLEU type: bleu value: 58.1 - name: chr-F type: chrf value: 0.76811 - task: name: Translation por-hun type: translation args: por-hun dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: por-hun metrics: - name: BLEU type: bleu value: 42.5 - name: chr-F type: chrf value: 0.64930 - task: name: Translation spa-fin type: translation args: spa-fin dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: spa-fin metrics: - name: BLEU type: bleu value: 43.4 - name: chr-F type: chrf value: 0.66220 - task: name: Translation spa-hun type: translation args: spa-hun dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: spa-hun metrics: - name: BLEU type: bleu value: 42.0 - name: chr-F type: chrf value: 0.63596 - task: name: Translation deu-hun type: translation args: deu-hun dataset: name: newstest2008 type: wmt-2008-news args: deu-hun metrics: - name: BLEU type: bleu value: 17.2 - name: chr-F type: chrf value: 0.48855 - task: name: Translation eng-hun type: translation args: eng-hun dataset: name: newstest2008 type: wmt-2008-news args: eng-hun metrics: - name: BLEU type: bleu value: 15.9 - name: chr-F type: chrf value: 0.47636 - task: name: Translation fra-hun type: translation args: fra-hun dataset: name: newstest2008 type: wmt-2008-news args: fra-hun metrics: - name: BLEU type: bleu value: 17.7 - name: chr-F type: chrf value: 0.48598 - task: name: Translation spa-hun type: translation args: spa-hun dataset: name: newstest2008 type: wmt-2008-news args: spa-hun metrics: - name: BLEU type: bleu value: 17.1 - name: chr-F type: chrf value: 0.47888 - task: name: Translation deu-hun type: translation args: deu-hun dataset: name: newstest2009 type: wmt-2009-news args: deu-hun metrics: - name: BLEU type: bleu value: 18.1 - name: chr-F type: chrf value: 0.48692 - task: name: Translation eng-hun type: translation args: eng-hun dataset: name: newstest2009 type: wmt-2009-news args: eng-hun metrics: - name: BLEU type: bleu value: 18.4 - name: chr-F type: chrf value: 0.49507 - task: name: Translation fra-hun type: translation args: fra-hun dataset: name: newstest2009 type: wmt-2009-news args: fra-hun metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.48961 - task: name: Translation spa-hun type: translation args: spa-hun dataset: name: newstest2009 type: wmt-2009-news args: spa-hun metrics: - name: BLEU type: bleu value: 18.1 - name: chr-F type: chrf value: 0.48496 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstest2015 type: wmt-2015-news args: eng-fin metrics: - name: BLEU type: bleu value: 22.8 - name: chr-F type: chrf value: 0.56896 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstest2016 type: wmt-2016-news args: eng-fin metrics: - name: BLEU type: bleu value: 24.3 - name: chr-F type: chrf value: 0.57934 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstest2017 type: wmt-2017-news args: eng-fin metrics: - name: BLEU type: bleu value: 26.5 - name: chr-F type: chrf value: 0.60204 - task: name: Translation eng-est type: translation args: eng-est dataset: name: newstest2018 type: wmt-2018-news args: eng-est metrics: - name: BLEU type: bleu value: 23.8 - name: chr-F type: chrf value: 0.56276 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstest2018 type: wmt-2018-news args: eng-fin metrics: - name: BLEU type: bleu value: 17.4 - name: chr-F type: chrf value: 0.52953 - task: name: Translation eng-fin type: translation args: eng-fin dataset: name: newstest2019 type: wmt-2019-news args: eng-fin metrics: - name: BLEU type: bleu value: 24.2 - name: chr-F type: chrf value: 0.55882 --- # opus-mt-tc-bible-big-deu_eng_fra_por_spa-fiu ## 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 unknown (deu+eng+fra+por+spa) to Finno-Ugrian languages (fiu). 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): deu eng fra por spa - Target Language(s): chm est fin fkv hun izh koi kom kpv krl liv mdf mrj myv sma sme smn udm vep vot vro - Valid Target Language Labels: >>chm<< >>est<< >>fin<< >>fit<< >>fkv<< >>fkv_Latn<< >>hun<< >>izh<< >>kca<< >>koi<< >>kom<< >>kpv<< >>krl<< >>liv<< >>liv_Latn<< >>mdf<< >>mns<< >>mrj<< >>myv<< >>olo<< >>sia<< >>sjd<< >>sje<< >>sjk<< >>sjt<< >>sju<< >>sma<< >>sme<< >>smj<< >>smn<< >>sms<< >>udm<< >>vep<< >>vot<< >>vot_Latn<< >>vro<< - **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-fiu/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/deu%2Beng%2Bfra%2Bpor%2Bspa-fiu/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. `>>chm<<` ## 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 = [ ">>chm<< Replace this with text in an accepted source language.", ">>vro<< This is the second sentence." ] model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-fiu" 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-deu_eng_fra_por_spa-fiu") print(pipe(">>chm<< 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/deu+eng+fra+por+spa-fiu/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/deu%2Beng%2Bfra%2Bpor%2Bspa-fiu/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/deu+eng+fra+por+spa-fiu/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/deu+eng+fra+por+spa-fiu/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 | |----------|---------|-------|-------|-------|--------| | deu-est | tatoeba-test-v2021-08-07 | 0.76586 | 57.8 | 244 | 1413 | | deu-fin | tatoeba-test-v2021-08-07 | 0.64286 | 40.7 | 2647 | 15024 | | deu-hun | tatoeba-test-v2021-08-07 | 0.57007 | 31.2 | 15342 | 105152 | | eng-est | tatoeba-test-v2021-08-07 | 0.69134 | 50.6 | 1359 | 7992 | | eng-fin | tatoeba-test-v2021-08-07 | 0.62482 | 37.6 | 10690 | 65122 | | eng-hun | tatoeba-test-v2021-08-07 | 0.59750 | 35.9 | 13037 | 79562 | | fra-fin | tatoeba-test-v2021-08-07 | 0.65723 | 45.0 | 1920 | 9730 | | fra-hun | tatoeba-test-v2021-08-07 | 0.63096 | 40.6 | 2494 | 13753 | | por-fin | tatoeba-test-v2021-08-07 | 0.76811 | 58.1 | 477 | 2379 | | por-hun | tatoeba-test-v2021-08-07 | 0.64930 | 42.5 | 2500 | 14063 | | spa-fin | tatoeba-test-v2021-08-07 | 0.66220 | 43.4 | 2513 | 14131 | | spa-hun | tatoeba-test-v2021-08-07 | 0.63596 | 42.0 | 2500 | 14599 | | eng-fin | flores101-devtest | 0.57265 | 21.9 | 1012 | 18781 | | fra-hun | flores101-devtest | 0.52691 | 21.2 | 1012 | 22183 | | por-fin | flores101-devtest | 0.53772 | 18.6 | 1012 | 18781 | | por-hun | flores101-devtest | 0.53275 | 21.8 | 1012 | 22183 | | spa-est | flores101-devtest | 0.50142 | 15.2 | 1012 | 19788 | | spa-fin | flores101-devtest | 0.50401 | 13.7 | 1012 | 18781 | | deu-est | flores200-devtest | 0.55333 | 21.2 | 1012 | 19788 | | deu-fin | flores200-devtest | 0.54020 | 18.3 | 1012 | 18781 | | deu-hun | flores200-devtest | 0.53579 | 22.0 | 1012 | 22183 | | eng-est | flores200-devtest | 0.59496 | 26.1 | 1012 | 19788 | | eng-fin | flores200-devtest | 0.57811 | 23.1 | 1012 | 18781 | | eng-hun | flores200-devtest | 0.57670 | 26.7 | 1012 | 22183 | | fra-est | flores200-devtest | 0.54442 | 21.2 | 1012 | 19788 | | fra-fin | flores200-devtest | 0.53768 | 18.5 | 1012 | 18781 | | fra-hun | flores200-devtest | 0.52691 | 21.2 | 1012 | 22183 | | por-est | flores200-devtest | 0.48227 | 15.6 | 1012 | 19788 | | por-fin | flores200-devtest | 0.53772 | 18.6 | 1012 | 18781 | | por-hun | flores200-devtest | 0.53275 | 21.8 | 1012 | 22183 | | spa-est | flores200-devtest | 0.50142 | 15.2 | 1012 | 19788 | | spa-fin | flores200-devtest | 0.50401 | 13.7 | 1012 | 18781 | | spa-hun | flores200-devtest | 0.49444 | 16.4 | 1012 | 22183 | | deu-hun | newssyscomb2009 | 0.49607 | 18.1 | 502 | 9733 | | eng-hun | newssyscomb2009 | 0.50580 | 18.3 | 502 | 9733 | | fra-hun | newssyscomb2009 | 0.49415 | 17.8 | 502 | 9733 | | spa-hun | newssyscomb2009 | 0.48559 | 16.9 | 502 | 9733 | | deu-hun | newstest2008 | 0.48855 | 17.2 | 2051 | 41875 | | eng-hun | newstest2008 | 0.47636 | 15.9 | 2051 | 41875 | | fra-hun | newstest2008 | 0.48598 | 17.7 | 2051 | 41875 | | spa-hun | newstest2008 | 0.47888 | 17.1 | 2051 | 41875 | | deu-hun | newstest2009 | 0.48692 | 18.1 | 2525 | 54965 | | eng-hun | newstest2009 | 0.49507 | 18.4 | 2525 | 54965 | | fra-hun | newstest2009 | 0.48961 | 18.6 | 2525 | 54965 | | spa-hun | newstest2009 | 0.48496 | 18.1 | 2525 | 54965 | | eng-fin | newstest2015 | 0.56896 | 22.8 | 1370 | 19735 | | eng-fin | newstest2016 | 0.57934 | 24.3 | 3000 | 47678 | | eng-fin | newstest2017 | 0.60204 | 26.5 | 3002 | 45269 | | eng-est | newstest2018 | 0.56276 | 23.8 | 2000 | 36269 | | eng-fin | newstest2018 | 0.52953 | 17.4 | 3000 | 44836 | | eng-fin | newstest2019 | 0.55882 | 24.2 | 1997 | 38369 | | eng-fin | newstestALL2016 | 0.57934 | 24.3 | 3000 | 47678 | | eng-fin | newstestALL2017 | 0.60204 | 26.5 | 3002 | 45269 | | eng-fin | newstestB2016 | 0.54388 | 19.9 | 3000 | 45766 | | eng-fin | newstestB2017 | 0.56369 | 22.6 | 3002 | 45506 | | deu-est | ntrex128 | 0.51761 | 18.6 | 1997 | 38420 | | deu-fin | ntrex128 | 0.50759 | 15.5 | 1997 | 35701 | | deu-hun | ntrex128 | 0.46171 | 15.6 | 1997 | 44462 | | eng-est | ntrex128 | 0.57099 | 24.4 | 1997 | 38420 | | eng-fin | ntrex128 | 0.53413 | 18.5 | 1997 | 35701 | | eng-hun | ntrex128 | 0.47342 | 16.6 | 1997 | 44462 | | fra-est | ntrex128 | 0.50712 | 17.7 | 1997 | 38420 | | fra-fin | ntrex128 | 0.49215 | 14.2 | 1997 | 35701 | | fra-hun | ntrex128 | 0.44873 | 14.9 | 1997 | 44462 | | por-est | ntrex128 | 0.48098 | 15.1 | 1997 | 38420 | | por-fin | ntrex128 | 0.50875 | 15.0 | 1997 | 35701 | | por-hun | ntrex128 | 0.45817 | 15.5 | 1997 | 44462 | | spa-est | ntrex128 | 0.52158 | 18.5 | 1997 | 38420 | | spa-fin | ntrex128 | 0.50947 | 15.2 | 1997 | 35701 | | spa-hun | ntrex128 | 0.46051 | 16.1 | 1997 | 44462 | ## 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 09:01:19 EEST 2024 * port machine: LM0-400-22516.local