--- 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-fiu-deu_eng_fra_por_spa results: - task: name: Translation est-deu type: translation args: est-deu dataset: name: flores200-devtest type: flores200-devtest args: est-deu metrics: - name: BLEU type: bleu value: 26.3 - name: chr-F type: chrf value: 0.55825 - task: name: Translation est-eng type: translation args: est-eng dataset: name: flores200-devtest type: flores200-devtest args: est-eng metrics: - name: BLEU type: bleu value: 35.4 - name: chr-F type: chrf value: 0.62404 - task: name: Translation est-fra type: translation args: est-fra dataset: name: flores200-devtest type: flores200-devtest args: est-fra metrics: - name: BLEU type: bleu value: 31.7 - name: chr-F type: chrf value: 0.58580 - task: name: Translation est-por type: translation args: est-por dataset: name: flores200-devtest type: flores200-devtest args: est-por metrics: - name: BLEU type: bleu value: 27.3 - name: chr-F type: chrf value: 0.55070 - task: name: Translation est-spa type: translation args: est-spa dataset: name: flores200-devtest type: flores200-devtest args: est-spa metrics: - name: BLEU type: bleu value: 21.5 - name: chr-F type: chrf value: 0.50188 - task: name: Translation fin-deu type: translation args: fin-deu dataset: name: flores200-devtest type: flores200-devtest args: fin-deu metrics: - name: BLEU type: bleu value: 24.0 - name: chr-F type: chrf value: 0.54281 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: flores200-devtest type: flores200-devtest args: fin-eng metrics: - name: BLEU type: bleu value: 33.1 - name: chr-F type: chrf value: 0.60642 - task: name: Translation fin-fra type: translation args: fin-fra dataset: name: flores200-devtest type: flores200-devtest args: fin-fra metrics: - name: BLEU type: bleu value: 30.5 - name: chr-F type: chrf value: 0.57540 - task: name: Translation fin-por type: translation args: fin-por dataset: name: flores200-devtest type: flores200-devtest args: fin-por metrics: - name: BLEU type: bleu value: 27.4 - name: chr-F type: chrf value: 0.55497 - task: name: Translation fin-spa type: translation args: fin-spa dataset: name: flores200-devtest type: flores200-devtest args: fin-spa metrics: - name: BLEU type: bleu value: 21.4 - name: chr-F type: chrf value: 0.49847 - task: name: Translation hun-deu type: translation args: hun-deu dataset: name: flores200-devtest type: flores200-devtest args: hun-deu metrics: - name: BLEU type: bleu value: 25.1 - name: chr-F type: chrf value: 0.55180 - task: name: Translation hun-eng type: translation args: hun-eng dataset: name: flores200-devtest type: flores200-devtest args: hun-eng metrics: - name: BLEU type: bleu value: 34.0 - name: chr-F type: chrf value: 0.61466 - task: name: Translation hun-fra type: translation args: hun-fra dataset: name: flores200-devtest type: flores200-devtest args: hun-fra metrics: - name: BLEU type: bleu value: 30.6 - name: chr-F type: chrf value: 0.57670 - task: name: Translation hun-por type: translation args: hun-por dataset: name: flores200-devtest type: flores200-devtest args: hun-por metrics: - name: BLEU type: bleu value: 28.9 - name: chr-F type: chrf value: 0.56510 - task: name: Translation hun-spa type: translation args: hun-spa dataset: name: flores200-devtest type: flores200-devtest args: hun-spa metrics: - name: BLEU type: bleu value: 21.3 - name: chr-F type: chrf value: 0.49681 - task: name: Translation est-deu type: translation args: est-deu dataset: name: flores101-devtest type: flores_101 args: est deu devtest metrics: - name: BLEU type: bleu value: 25.7 - name: chr-F type: chrf value: 0.55353 - task: name: Translation est-eng type: translation args: est-eng dataset: name: flores101-devtest type: flores_101 args: est eng devtest metrics: - name: BLEU type: bleu value: 34.7 - name: chr-F type: chrf value: 0.61930 - task: name: Translation est-fra type: translation args: est-fra dataset: name: flores101-devtest type: flores_101 args: est fra devtest metrics: - name: BLEU type: bleu value: 31.3 - name: chr-F type: chrf value: 0.58199 - task: name: Translation est-por type: translation args: est-por dataset: name: flores101-devtest type: flores_101 args: est por devtest metrics: - name: BLEU type: bleu value: 26.5 - name: chr-F type: chrf value: 0.54388 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: flores101-devtest type: flores_101 args: fin eng devtest metrics: - name: BLEU type: bleu value: 32.2 - name: chr-F type: chrf value: 0.59914 - task: name: Translation fin-por type: translation args: fin-por dataset: name: flores101-devtest type: flores_101 args: fin por devtest metrics: - name: BLEU type: bleu value: 27.1 - name: chr-F type: chrf value: 0.55156 - task: name: Translation hun-eng type: translation args: hun-eng dataset: name: flores101-devtest type: flores_101 args: hun eng devtest metrics: - name: BLEU type: bleu value: 33.5 - name: chr-F type: chrf value: 0.61198 - task: name: Translation hun-fra type: translation args: hun-fra dataset: name: flores101-devtest type: flores_101 args: hun fra devtest metrics: - name: BLEU type: bleu value: 30.8 - name: chr-F type: chrf value: 0.57776 - task: name: Translation hun-por type: translation args: hun-por dataset: name: flores101-devtest type: flores_101 args: hun por devtest metrics: - name: BLEU type: bleu value: 28.4 - name: chr-F type: chrf value: 0.56263 - task: name: Translation hun-spa type: translation args: hun-spa dataset: name: flores101-devtest type: flores_101 args: hun spa devtest metrics: - name: BLEU type: bleu value: 20.7 - name: chr-F type: chrf value: 0.49140 - task: name: Translation est-deu type: translation args: est-deu dataset: name: ntrex128 type: ntrex128 args: est-deu metrics: - name: BLEU type: bleu value: 21.4 - name: chr-F type: chrf value: 0.51377 - task: name: Translation est-eng type: translation args: est-eng dataset: name: ntrex128 type: ntrex128 args: est-eng metrics: - name: BLEU type: bleu value: 29.9 - name: chr-F type: chrf value: 0.58358 - task: name: Translation est-fra type: translation args: est-fra dataset: name: ntrex128 type: ntrex128 args: est-fra metrics: - name: BLEU type: bleu value: 24.9 - name: chr-F type: chrf value: 0.52713 - task: name: Translation est-por type: translation args: est-por dataset: name: ntrex128 type: ntrex128 args: est-por metrics: - name: BLEU type: bleu value: 22.2 - name: chr-F type: chrf value: 0.50745 - task: name: Translation est-spa type: translation args: est-spa dataset: name: ntrex128 type: ntrex128 args: est-spa metrics: - name: BLEU type: bleu value: 27.5 - name: chr-F type: chrf value: 0.54304 - task: name: Translation fin-deu type: translation args: fin-deu dataset: name: ntrex128 type: ntrex128 args: fin-deu metrics: - name: BLEU type: bleu value: 19.8 - name: chr-F type: chrf value: 0.50282 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: ntrex128 type: ntrex128 args: fin-eng metrics: - name: BLEU type: bleu value: 26.3 - name: chr-F type: chrf value: 0.55545 - task: name: Translation fin-fra type: translation args: fin-fra dataset: name: ntrex128 type: ntrex128 args: fin-fra metrics: - name: BLEU type: bleu value: 22.9 - name: chr-F type: chrf value: 0.50946 - task: name: Translation fin-por type: translation args: fin-por dataset: name: ntrex128 type: ntrex128 args: fin-por metrics: - name: BLEU type: bleu value: 21.3 - name: chr-F type: chrf value: 0.50404 - task: name: Translation fin-spa type: translation args: fin-spa dataset: name: ntrex128 type: ntrex128 args: fin-spa metrics: - name: BLEU type: bleu value: 25.5 - name: chr-F type: chrf value: 0.52641 - task: name: Translation hun-deu type: translation args: hun-deu dataset: name: ntrex128 type: ntrex128 args: hun-deu metrics: - name: BLEU type: bleu value: 18.5 - name: chr-F type: chrf value: 0.49322 - task: name: Translation hun-eng type: translation args: hun-eng dataset: name: ntrex128 type: ntrex128 args: hun-eng metrics: - name: BLEU type: bleu value: 23.3 - name: chr-F type: chrf value: 0.52964 - task: name: Translation hun-fra type: translation args: hun-fra dataset: name: ntrex128 type: ntrex128 args: hun-fra metrics: - name: BLEU type: bleu value: 21.8 - name: chr-F type: chrf value: 0.49800 - task: name: Translation hun-por type: translation args: hun-por dataset: name: ntrex128 type: ntrex128 args: hun-por metrics: - name: BLEU type: bleu value: 20.5 - name: chr-F type: chrf value: 0.48941 - task: name: Translation hun-spa type: translation args: hun-spa dataset: name: ntrex128 type: ntrex128 args: hun-spa metrics: - name: BLEU type: bleu value: 24.2 - name: chr-F type: chrf value: 0.51123 - task: name: Translation est-deu type: translation args: est-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: est-deu metrics: - name: BLEU type: bleu value: 53.9 - name: chr-F type: chrf value: 0.69451 - task: name: Translation est-eng type: translation args: est-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: est-eng metrics: - name: BLEU type: bleu value: 58.2 - name: chr-F type: chrf value: 0.72437 - task: name: Translation fin-deu type: translation args: fin-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fin-deu metrics: - name: BLEU type: bleu value: 47.3 - name: chr-F type: chrf value: 0.66025 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fin-eng metrics: - name: BLEU type: bleu value: 53.7 - name: chr-F type: chrf value: 0.69685 - task: name: Translation fin-fra type: translation args: fin-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fin-fra metrics: - name: BLEU type: bleu value: 48.3 - name: chr-F type: chrf value: 0.65900 - task: name: Translation fin-por type: translation args: fin-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fin-por metrics: - name: BLEU type: bleu value: 54.0 - name: chr-F type: chrf value: 0.72250 - task: name: Translation fin-spa type: translation args: fin-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fin-spa metrics: - name: BLEU type: bleu value: 52.1 - name: chr-F type: chrf value: 0.69600 - task: name: Translation hun-deu type: translation args: hun-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: hun-deu metrics: - name: BLEU type: bleu value: 41.1 - name: chr-F type: chrf value: 0.62418 - task: name: Translation hun-eng type: translation args: hun-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: hun-eng metrics: - name: BLEU type: bleu value: 48.7 - name: chr-F type: chrf value: 0.65626 - task: name: Translation hun-fra type: translation args: hun-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: hun-fra metrics: - name: BLEU type: bleu value: 50.3 - name: chr-F type: chrf value: 0.66840 - task: name: Translation hun-por type: translation args: hun-por dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: hun-por metrics: - name: BLEU type: bleu value: 43.1 - name: chr-F type: chrf value: 0.65281 - task: name: Translation hun-spa type: translation args: hun-spa dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: hun-spa metrics: - name: BLEU type: bleu value: 48.7 - name: chr-F type: chrf value: 0.67467 - 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: 44.6 - name: chr-F type: chrf value: 0.63895 - task: name: Translation hun-deu type: translation args: hun-deu dataset: name: newstest2008 type: wmt-2008-news args: hun-deu metrics: - name: BLEU type: bleu value: 19.0 - name: chr-F type: chrf value: 0.50164 - task: name: Translation hun-eng type: translation args: hun-eng dataset: name: newstest2008 type: wmt-2008-news args: hun-eng metrics: - name: BLEU type: bleu value: 20.4 - name: chr-F type: chrf value: 0.49802 - task: name: Translation hun-fra type: translation args: hun-fra dataset: name: newstest2008 type: wmt-2008-news args: hun-fra metrics: - name: BLEU type: bleu value: 21.6 - name: chr-F type: chrf value: 0.51012 - task: name: Translation hun-spa type: translation args: hun-spa dataset: name: newstest2008 type: wmt-2008-news args: hun-spa metrics: - name: BLEU type: bleu value: 22.3 - name: chr-F type: chrf value: 0.50719 - task: name: Translation hun-deu type: translation args: hun-deu dataset: name: newstest2009 type: wmt-2009-news args: hun-deu metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.49902 - task: name: Translation hun-eng type: translation args: hun-eng dataset: name: newstest2009 type: wmt-2009-news args: hun-eng metrics: - name: BLEU type: bleu value: 22.3 - name: chr-F type: chrf value: 0.50950 - task: name: Translation hun-fra type: translation args: hun-fra dataset: name: newstest2009 type: wmt-2009-news args: hun-fra metrics: - name: BLEU type: bleu value: 21.6 - name: chr-F type: chrf value: 0.50742 - task: name: Translation hun-spa type: translation args: hun-spa dataset: name: newstest2009 type: wmt-2009-news args: hun-spa metrics: - name: BLEU type: bleu value: 22.2 - name: chr-F type: chrf value: 0.50788 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: newstest2015 type: wmt-2015-news args: fin-eng metrics: - name: BLEU type: bleu value: 27.0 - name: chr-F type: chrf value: 0.55249 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: newstest2016 type: wmt-2016-news args: fin-eng metrics: - name: BLEU type: bleu value: 30.7 - name: chr-F type: chrf value: 0.57961 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: newstest2017 type: wmt-2017-news args: fin-eng metrics: - name: BLEU type: bleu value: 33.2 - name: chr-F type: chrf value: 0.59973 - task: name: Translation est-eng type: translation args: est-eng dataset: name: newstest2018 type: wmt-2018-news args: est-eng metrics: - name: BLEU type: bleu value: 31.5 - name: chr-F type: chrf value: 0.59190 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: newstest2018 type: wmt-2018-news args: fin-eng metrics: - name: BLEU type: bleu value: 24.4 - name: chr-F type: chrf value: 0.52373 - task: name: Translation fin-eng type: translation args: fin-eng dataset: name: newstest2019 type: wmt-2019-news args: fin-eng metrics: - name: BLEU type: bleu value: 30.3 - name: chr-F type: chrf value: 0.57079 --- # opus-mt-tc-bible-big-fiu-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 Finno-Ugrian languages (fiu) 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): chm est fin fkv hun izh koi kom kpv krl liv mdf mrj myv sma sme smn udm vep vot vro - 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/fiu-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/fiu-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-fiu-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-fiu-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/fiu-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/fiu-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/fiu-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/fiu-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 | |----------|---------|-------|-------|-------|--------| | est-deu | tatoeba-test-v2021-08-07 | 0.69451 | 53.9 | 244 | 1611 | | est-eng | tatoeba-test-v2021-08-07 | 0.72437 | 58.2 | 1359 | 8811 | | fin-deu | tatoeba-test-v2021-08-07 | 0.66025 | 47.3 | 2647 | 19163 | | fin-eng | tatoeba-test-v2021-08-07 | 0.69685 | 53.7 | 10690 | 80552 | | fin-fra | tatoeba-test-v2021-08-07 | 0.65900 | 48.3 | 1920 | 12193 | | fin-por | tatoeba-test-v2021-08-07 | 0.72250 | 54.0 | 477 | 3021 | | fin-spa | tatoeba-test-v2021-08-07 | 0.69600 | 52.1 | 2513 | 16912 | | hun-deu | tatoeba-test-v2021-08-07 | 0.62418 | 41.1 | 15342 | 127344 | | hun-eng | tatoeba-test-v2021-08-07 | 0.65626 | 48.7 | 13037 | 94699 | | hun-fra | tatoeba-test-v2021-08-07 | 0.66840 | 50.3 | 2494 | 16914 | | hun-por | tatoeba-test-v2021-08-07 | 0.65281 | 43.1 | 2500 | 16563 | | hun-spa | tatoeba-test-v2021-08-07 | 0.67467 | 48.7 | 2500 | 16670 | | est-deu | flores101-devtest | 0.55353 | 25.7 | 1012 | 25094 | | est-eng | flores101-devtest | 0.61930 | 34.7 | 1012 | 24721 | | est-fra | flores101-devtest | 0.58199 | 31.3 | 1012 | 28343 | | est-por | flores101-devtest | 0.54388 | 26.5 | 1012 | 26519 | | fin-eng | flores101-devtest | 0.59914 | 32.2 | 1012 | 24721 | | fin-por | flores101-devtest | 0.55156 | 27.1 | 1012 | 26519 | | hun-eng | flores101-devtest | 0.61198 | 33.5 | 1012 | 24721 | | hun-fra | flores101-devtest | 0.57776 | 30.8 | 1012 | 28343 | | hun-por | flores101-devtest | 0.56263 | 28.4 | 1012 | 26519 | | hun-spa | flores101-devtest | 0.49140 | 20.7 | 1012 | 29199 | | est-deu | flores200-devtest | 0.55825 | 26.3 | 1012 | 25094 | | est-eng | flores200-devtest | 0.62404 | 35.4 | 1012 | 24721 | | est-fra | flores200-devtest | 0.58580 | 31.7 | 1012 | 28343 | | est-por | flores200-devtest | 0.55070 | 27.3 | 1012 | 26519 | | est-spa | flores200-devtest | 0.50188 | 21.5 | 1012 | 29199 | | fin-deu | flores200-devtest | 0.54281 | 24.0 | 1012 | 25094 | | fin-eng | flores200-devtest | 0.60642 | 33.1 | 1012 | 24721 | | fin-fra | flores200-devtest | 0.57540 | 30.5 | 1012 | 28343 | | fin-por | flores200-devtest | 0.55497 | 27.4 | 1012 | 26519 | | fin-spa | flores200-devtest | 0.49847 | 21.4 | 1012 | 29199 | | hun-deu | flores200-devtest | 0.55180 | 25.1 | 1012 | 25094 | | hun-eng | flores200-devtest | 0.61466 | 34.0 | 1012 | 24721 | | hun-fra | flores200-devtest | 0.57670 | 30.6 | 1012 | 28343 | | hun-por | flores200-devtest | 0.56510 | 28.9 | 1012 | 26519 | | hun-spa | flores200-devtest | 0.49681 | 21.3 | 1012 | 29199 | | hun-deu | newssyscomb2009 | 0.49819 | 17.9 | 502 | 11271 | | hun-eng | newssyscomb2009 | 0.52063 | 24.4 | 502 | 11818 | | hun-fra | newssyscomb2009 | 0.51589 | 22.0 | 502 | 12331 | | hun-spa | newssyscomb2009 | 0.51508 | 22.7 | 502 | 12503 | | hun-deu | newstest2008 | 0.50164 | 19.0 | 2051 | 47447 | | hun-eng | newstest2008 | 0.49802 | 20.4 | 2051 | 49380 | | hun-fra | newstest2008 | 0.51012 | 21.6 | 2051 | 52685 | | hun-spa | newstest2008 | 0.50719 | 22.3 | 2051 | 52586 | | hun-deu | newstest2009 | 0.49902 | 18.6 | 2525 | 62816 | | hun-eng | newstest2009 | 0.50950 | 22.3 | 2525 | 65399 | | hun-fra | newstest2009 | 0.50742 | 21.6 | 2525 | 69263 | | hun-spa | newstest2009 | 0.50788 | 22.2 | 2525 | 68111 | | fin-eng | newstest2015 | 0.55249 | 27.0 | 1370 | 27270 | | fin-eng | newstest2016 | 0.57961 | 30.7 | 3000 | 62945 | | fin-eng | newstest2017 | 0.59973 | 33.2 | 3002 | 61846 | | est-eng | newstest2018 | 0.59190 | 31.5 | 2000 | 45405 | | fin-eng | newstest2018 | 0.52373 | 24.4 | 3000 | 62325 | | fin-eng | newstest2019 | 0.57079 | 30.3 | 1996 | 36215 | | fin-eng | newstestB2017 | 0.56420 | 28.9 | 3002 | 61846 | | est-deu | ntrex128 | 0.51377 | 21.4 | 1997 | 48761 | | est-eng | ntrex128 | 0.58358 | 29.9 | 1997 | 47673 | | est-fra | ntrex128 | 0.52713 | 24.9 | 1997 | 53481 | | est-por | ntrex128 | 0.50745 | 22.2 | 1997 | 51631 | | est-spa | ntrex128 | 0.54304 | 27.5 | 1997 | 54107 | | fin-deu | ntrex128 | 0.50282 | 19.8 | 1997 | 48761 | | fin-eng | ntrex128 | 0.55545 | 26.3 | 1997 | 47673 | | fin-fra | ntrex128 | 0.50946 | 22.9 | 1997 | 53481 | | fin-por | ntrex128 | 0.50404 | 21.3 | 1997 | 51631 | | fin-spa | ntrex128 | 0.52641 | 25.5 | 1997 | 54107 | | hun-deu | ntrex128 | 0.49322 | 18.5 | 1997 | 48761 | | hun-eng | ntrex128 | 0.52964 | 23.3 | 1997 | 47673 | | hun-fra | ntrex128 | 0.49800 | 21.8 | 1997 | 53481 | | hun-por | ntrex128 | 0.48941 | 20.5 | 1997 | 51631 | | hun-spa | ntrex128 | 0.51123 | 24.2 | 1997 | 54107 | ## 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 10:53:49 EEST 2024 * port machine: LM0-400-22516.local