--- library_name: transformers language: - bal - de - diq - en - es - fa - fr - glk - jdt - ku - lrc - mzn - os - pal - ps - pt - tg - tly - zza language_bcp47: - ku_Latn tags: - translation - opus-mt-tc-bible license: apache-2.0 model-index: - name: opus-mt-tc-bible-big-ira-deu_eng_fra_por_spa results: - task: name: Translation ckb-deu type: translation args: ckb-deu dataset: name: flores200-devtest type: flores200-devtest args: ckb-deu metrics: - name: BLEU type: bleu value: 11.7 - name: chr-F type: chrf value: 0.40369 - task: name: Translation ckb-eng type: translation args: ckb-eng dataset: name: flores200-devtest type: flores200-devtest args: ckb-eng metrics: - name: BLEU type: bleu value: 21.5 - name: chr-F type: chrf value: 0.48447 - task: name: Translation ckb-fra type: translation args: ckb-fra dataset: name: flores200-devtest type: flores200-devtest args: ckb-fra metrics: - name: BLEU type: bleu value: 17.1 - name: chr-F type: chrf value: 0.44026 - task: name: Translation ckb-por type: translation args: ckb-por dataset: name: flores200-devtest type: flores200-devtest args: ckb-por metrics: - name: BLEU type: bleu value: 16.4 - name: chr-F type: chrf value: 0.43192 - task: name: Translation ckb-spa type: translation args: ckb-spa dataset: name: flores200-devtest type: flores200-devtest args: ckb-spa metrics: - name: BLEU type: bleu value: 11.7 - name: chr-F type: chrf value: 0.38880 - task: name: Translation kmr-eng type: translation args: kmr-eng dataset: name: flores200-devtest type: flores200-devtest args: kmr-eng metrics: - name: BLEU type: bleu value: 12.4 - name: chr-F type: chrf value: 0.37372 - task: name: Translation pes-deu type: translation args: pes-deu dataset: name: flores200-devtest type: flores200-devtest args: pes-deu metrics: - name: BLEU type: bleu value: 21.5 - name: chr-F type: chrf value: 0.51542 - task: name: Translation pes-eng type: translation args: pes-eng dataset: name: flores200-devtest type: flores200-devtest args: pes-eng metrics: - name: BLEU type: bleu value: 34.9 - name: chr-F type: chrf value: 0.61372 - task: name: Translation pes-fra type: translation args: pes-fra dataset: name: flores200-devtest type: flores200-devtest args: pes-fra metrics: - name: BLEU type: bleu value: 29.2 - name: chr-F type: chrf value: 0.56347 - task: name: Translation pes-por type: translation args: pes-por dataset: name: flores200-devtest type: flores200-devtest args: pes-por metrics: - name: BLEU type: bleu value: 28.5 - name: chr-F type: chrf value: 0.55676 - task: name: Translation pes-spa type: translation args: pes-spa dataset: name: flores200-devtest type: flores200-devtest args: pes-spa metrics: - name: BLEU type: bleu value: 19.8 - name: chr-F type: chrf value: 0.48334 - task: name: Translation prs-deu type: translation args: prs-deu dataset: name: flores200-devtest type: flores200-devtest args: prs-deu metrics: - name: BLEU type: bleu value: 21.2 - name: chr-F type: chrf value: 0.50562 - task: name: Translation prs-eng type: translation args: prs-eng dataset: name: flores200-devtest type: flores200-devtest args: prs-eng metrics: - name: BLEU type: bleu value: 35.1 - name: chr-F type: chrf value: 0.60716 - task: name: Translation prs-fra type: translation args: prs-fra dataset: name: flores200-devtest type: flores200-devtest args: prs-fra metrics: - name: BLEU type: bleu value: 27.8 - name: chr-F type: chrf value: 0.54769 - task: name: Translation prs-por type: translation args: prs-por dataset: name: flores200-devtest type: flores200-devtest args: prs-por metrics: - name: BLEU type: bleu value: 27.2 - name: chr-F type: chrf value: 0.54073 - task: name: Translation prs-spa type: translation args: prs-spa dataset: name: flores200-devtest type: flores200-devtest args: prs-spa metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.46850 - task: name: Translation tgk-deu type: translation args: tgk-deu dataset: name: flores200-devtest type: flores200-devtest args: tgk-deu metrics: - name: BLEU type: bleu value: 14.2 - name: chr-F type: chrf value: 0.43115 - task: name: Translation tgk-eng type: translation args: tgk-eng dataset: name: flores200-devtest type: flores200-devtest args: tgk-eng metrics: - name: BLEU type: bleu value: 25.6 - name: chr-F type: chrf value: 0.53705 - task: name: Translation tgk-fra type: translation args: tgk-fra dataset: name: flores200-devtest type: flores200-devtest args: tgk-fra metrics: - name: BLEU type: bleu value: 20.7 - name: chr-F type: chrf value: 0.48902 - task: name: Translation tgk-por type: translation args: tgk-por dataset: name: flores200-devtest type: flores200-devtest args: tgk-por metrics: - name: BLEU type: bleu value: 20.7 - name: chr-F type: chrf value: 0.48519 - task: name: Translation tgk-spa type: translation args: tgk-spa dataset: name: flores200-devtest type: flores200-devtest args: tgk-spa metrics: - name: BLEU type: bleu value: 15.7 - name: chr-F type: chrf value: 0.43563 - task: name: Translation ckb-deu type: translation args: ckb-deu dataset: name: flores101-devtest type: flores_101 args: ckb deu devtest metrics: - name: BLEU type: bleu value: 11.6 - name: chr-F type: chrf value: 0.40117 - task: name: Translation ckb-eng type: translation args: ckb-eng dataset: name: flores101-devtest type: flores_101 args: ckb eng devtest metrics: - name: BLEU type: bleu value: 21.6 - name: chr-F type: chrf value: 0.48321 - task: name: Translation ckb-fra type: translation args: ckb-fra dataset: name: flores101-devtest type: flores_101 args: ckb fra devtest metrics: - name: BLEU type: bleu value: 17.2 - name: chr-F type: chrf value: 0.44260 - task: name: Translation ckb-por type: translation args: ckb-por dataset: name: flores101-devtest type: flores_101 args: ckb por devtest metrics: - name: BLEU type: bleu value: 16.2 - name: chr-F type: chrf value: 0.43179 - task: name: Translation fas-eng type: translation args: fas-eng dataset: name: flores101-devtest type: flores_101 args: fas eng devtest metrics: - name: BLEU type: bleu value: 34.4 - name: chr-F type: chrf value: 0.61134 - task: name: Translation pus-eng type: translation args: pus-eng dataset: name: flores101-devtest type: flores_101 args: pus eng devtest metrics: - name: BLEU type: bleu value: 22.7 - name: chr-F type: chrf value: 0.49556 - task: name: Translation pus-fra type: translation args: pus-fra dataset: name: flores101-devtest type: flores_101 args: pus fra devtest metrics: - name: BLEU type: bleu value: 17.8 - name: chr-F type: chrf value: 0.45248 - task: name: Translation tgk-eng type: translation args: tgk-eng dataset: name: flores101-devtest type: flores_101 args: tgk eng devtest metrics: - name: BLEU type: bleu value: 25.4 - name: chr-F type: chrf value: 0.53630 - task: name: Translation tgk-fra type: translation args: tgk-fra dataset: name: flores101-devtest type: flores_101 args: tgk fra devtest metrics: - name: BLEU type: bleu value: 21.0 - name: chr-F type: chrf value: 0.49084 - task: name: Translation tgk-spa type: translation args: tgk-spa dataset: name: flores101-devtest type: flores_101 args: tgk spa devtest metrics: - name: BLEU type: bleu value: 15.5 - name: chr-F type: chrf value: 0.43524 - task: name: Translation fas-deu type: translation args: fas-deu dataset: name: ntrex128 type: ntrex128 args: fas-deu metrics: - name: BLEU type: bleu value: 16.7 - name: chr-F type: chrf value: 0.47408 - task: name: Translation fas-eng type: translation args: fas-eng dataset: name: ntrex128 type: ntrex128 args: fas-eng metrics: - name: BLEU type: bleu value: 26.4 - name: chr-F type: chrf value: 0.55350 - task: name: Translation fas-fra type: translation args: fas-fra dataset: name: ntrex128 type: ntrex128 args: fas-fra metrics: - name: BLEU type: bleu value: 22.1 - name: chr-F type: chrf value: 0.50311 - task: name: Translation fas-por type: translation args: fas-por dataset: name: ntrex128 type: ntrex128 args: fas-por metrics: - name: BLEU type: bleu value: 19.1 - name: chr-F type: chrf value: 0.48005 - task: name: Translation fas-spa type: translation args: fas-spa dataset: name: ntrex128 type: ntrex128 args: fas-spa metrics: - name: BLEU type: bleu value: 23.6 - name: chr-F type: chrf value: 0.50973 - task: name: Translation kmr-eng type: translation args: kmr-eng dataset: name: ntrex128 type: ntrex128 args: kmr-eng metrics: - name: BLEU type: bleu value: 12.8 - name: chr-F type: chrf value: 0.38189 - task: name: Translation prs-deu type: translation args: prs-deu dataset: name: ntrex128 type: ntrex128 args: prs-deu metrics: - name: BLEU type: bleu value: 14.9 - name: chr-F type: chrf value: 0.45191 - task: name: Translation prs-eng type: translation args: prs-eng dataset: name: ntrex128 type: ntrex128 args: prs-eng metrics: - name: BLEU type: bleu value: 26.6 - name: chr-F type: chrf value: 0.54761 - task: name: Translation prs-fra type: translation args: prs-fra dataset: name: ntrex128 type: ntrex128 args: prs-fra metrics: - name: BLEU type: bleu value: 19.9 - name: chr-F type: chrf value: 0.47819 - task: name: Translation prs-por type: translation args: prs-por dataset: name: ntrex128 type: ntrex128 args: prs-por metrics: - name: BLEU type: bleu value: 17.4 - name: chr-F type: chrf value: 0.46241 - task: name: Translation prs-spa type: translation args: prs-spa dataset: name: ntrex128 type: ntrex128 args: prs-spa metrics: - name: BLEU type: bleu value: 21.4 - name: chr-F type: chrf value: 0.48712 - task: name: Translation pus-eng type: translation args: pus-eng dataset: name: ntrex128 type: ntrex128 args: pus-eng metrics: - name: BLEU type: bleu value: 17.4 - name: chr-F type: chrf value: 0.43901 - task: name: Translation pus-fra type: translation args: pus-fra dataset: name: ntrex128 type: ntrex128 args: pus-fra metrics: - name: BLEU type: bleu value: 12.4 - name: chr-F type: chrf value: 0.39661 - task: name: Translation pus-por type: translation args: pus-por dataset: name: ntrex128 type: ntrex128 args: pus-por metrics: - name: BLEU type: bleu value: 11.4 - name: chr-F type: chrf value: 0.38694 - task: name: Translation pus-spa type: translation args: pus-spa dataset: name: ntrex128 type: ntrex128 args: pus-spa metrics: - name: BLEU type: bleu value: 14.1 - name: chr-F type: chrf value: 0.40812 - task: name: Translation tgk_Cyrl-deu type: translation args: tgk_Cyrl-deu dataset: name: ntrex128 type: ntrex128 args: tgk_Cyrl-deu metrics: - name: BLEU type: bleu value: 10.7 - name: chr-F type: chrf value: 0.38740 - task: name: Translation tgk_Cyrl-eng type: translation args: tgk_Cyrl-eng dataset: name: ntrex128 type: ntrex128 args: tgk_Cyrl-eng metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.46839 - task: name: Translation tgk_Cyrl-fra type: translation args: tgk_Cyrl-fra dataset: name: ntrex128 type: ntrex128 args: tgk_Cyrl-fra metrics: - name: BLEU type: bleu value: 15.1 - name: chr-F type: chrf value: 0.42569 - task: name: Translation tgk_Cyrl-por type: translation args: tgk_Cyrl-por dataset: name: ntrex128 type: ntrex128 args: tgk_Cyrl-por metrics: - name: BLEU type: bleu value: 13.7 - name: chr-F type: chrf value: 0.41632 - task: name: Translation tgk_Cyrl-spa type: translation args: tgk_Cyrl-spa dataset: name: ntrex128 type: ntrex128 args: tgk_Cyrl-spa metrics: - name: BLEU type: bleu value: 16.8 - name: chr-F type: chrf value: 0.43763 - task: name: Translation fas-deu type: translation args: fas-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fas-deu metrics: - name: BLEU type: bleu value: 36.1 - name: chr-F type: chrf value: 0.59737 - task: name: Translation fas-eng type: translation args: fas-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fas-eng metrics: - name: BLEU type: bleu value: 35.8 - name: chr-F type: chrf value: 0.59871 - task: name: Translation fas-fra type: translation args: fas-fra dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fas-fra metrics: - name: BLEU type: bleu value: 36.3 - name: chr-F type: chrf value: 0.58095 - task: name: Translation kur_Latn-deu type: translation args: kur_Latn-deu dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: kur_Latn-deu metrics: - name: BLEU type: bleu value: 24.9 - name: chr-F type: chrf value: 0.40276 - 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: 34.0 - name: chr-F type: chrf value: 0.56042 - task: name: Translation pes-eng type: translation args: pes-eng dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: pes-eng metrics: - name: BLEU type: bleu value: 42.3 - name: chr-F type: chrf value: 0.60717 - task: name: Translation ckb-eng type: translation args: ckb-eng dataset: name: tico19-test type: tico19-test args: ckb-eng metrics: - name: BLEU type: bleu value: 40.1 - name: chr-F type: chrf value: 0.61905 - task: name: Translation ckb-fra type: translation args: ckb-fra dataset: name: tico19-test type: tico19-test args: ckb-fra metrics: - name: BLEU type: bleu value: 19.7 - name: chr-F type: chrf value: 0.45070 - task: name: Translation ckb-por type: translation args: ckb-por dataset: name: tico19-test type: tico19-test args: ckb-por metrics: - name: BLEU type: bleu value: 22.9 - name: chr-F type: chrf value: 0.49617 - task: name: Translation ckb-spa type: translation args: ckb-spa dataset: name: tico19-test type: tico19-test args: ckb-spa metrics: - name: BLEU type: bleu value: 24.9 - name: chr-F type: chrf value: 0.50543 - task: name: Translation fas-eng type: translation args: fas-eng dataset: name: tico19-test type: tico19-test args: fas-eng metrics: - name: BLEU type: bleu value: 37.3 - name: chr-F type: chrf value: 0.64016 - task: name: Translation fas-fra type: translation args: fas-fra dataset: name: tico19-test type: tico19-test args: fas-fra metrics: - name: BLEU type: bleu value: 26.1 - name: chr-F type: chrf value: 0.53319 - task: name: Translation fas-por type: translation args: fas-por dataset: name: tico19-test type: tico19-test args: fas-por metrics: - name: BLEU type: bleu value: 30.6 - name: chr-F type: chrf value: 0.58008 - task: name: Translation fas-spa type: translation args: fas-spa dataset: name: tico19-test type: tico19-test args: fas-spa metrics: - name: BLEU type: bleu value: 33.3 - name: chr-F type: chrf value: 0.59239 - task: name: Translation prs-eng type: translation args: prs-eng dataset: name: tico19-test type: tico19-test args: prs-eng metrics: - name: BLEU type: bleu value: 34.8 - name: chr-F type: chrf value: 0.61702 - task: name: Translation prs-fra type: translation args: prs-fra dataset: name: tico19-test type: tico19-test args: prs-fra metrics: - name: BLEU type: bleu value: 24.0 - name: chr-F type: chrf value: 0.51218 - task: name: Translation prs-por type: translation args: prs-por dataset: name: tico19-test type: tico19-test args: prs-por metrics: - name: BLEU type: bleu value: 28.6 - name: chr-F type: chrf value: 0.55888 - task: name: Translation prs-spa type: translation args: prs-spa dataset: name: tico19-test type: tico19-test args: prs-spa metrics: - name: BLEU type: bleu value: 31.1 - name: chr-F type: chrf value: 0.57494 - task: name: Translation pus-eng type: translation args: pus-eng dataset: name: tico19-test type: tico19-test args: pus-eng metrics: - name: BLEU type: bleu value: 32.1 - name: chr-F type: chrf value: 0.57586 - task: name: Translation pus-fra type: translation args: pus-fra dataset: name: tico19-test type: tico19-test args: pus-fra metrics: - name: BLEU type: bleu value: 19.2 - name: chr-F type: chrf value: 0.46091 - task: name: Translation pus-por type: translation args: pus-por dataset: name: tico19-test type: tico19-test args: pus-por metrics: - name: BLEU type: bleu value: 24.1 - name: chr-F type: chrf value: 0.51033 - task: name: Translation pus-spa type: translation args: pus-spa dataset: name: tico19-test type: tico19-test args: pus-spa metrics: - name: BLEU type: bleu value: 25.9 - name: chr-F type: chrf value: 0.51857 - task: name: Translation pus-eng type: translation args: pus-eng dataset: name: newstest2020 type: wmt-2020-news args: pus-eng metrics: - name: BLEU type: bleu value: 13.1 - name: chr-F type: chrf value: 0.37487 --- # opus-mt-tc-bible-big-ira-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 Iranian languages (ira) 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): bal ckb diq fas glk jdt kmr kur lrc mzn oss pal pes prs pus sdh tgk tly zza - 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/ira-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/ira-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-ira-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-ira-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/ira-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/ira-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/ira-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/ira-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 | |----------|---------|-------|-------|-------|--------| | fas-deu | tatoeba-test-v2021-08-07 | 0.59737 | 36.1 | 3185 | 25590 | | fas-eng | tatoeba-test-v2021-08-07 | 0.59871 | 35.8 | 3762 | 31480 | | fas-fra | tatoeba-test-v2021-08-07 | 0.58095 | 36.3 | 376 | 3377 | | kur_Latn-deu | tatoeba-test-v2021-08-07 | 0.40276 | 24.9 | 223 | 1323 | | pes-eng | tatoeba-test-v2021-08-07 | 0.60717 | 42.3 | 3757 | 31411 | | ckb-deu | flores101-devtest | 0.40117 | 11.6 | 1012 | 25094 | | ckb-eng | flores101-devtest | 0.48321 | 21.6 | 1012 | 24721 | | ckb-fra | flores101-devtest | 0.44260 | 17.2 | 1012 | 28343 | | ckb-por | flores101-devtest | 0.43179 | 16.2 | 1012 | 26519 | | fas-eng | flores101-devtest | 0.61134 | 34.4 | 1012 | 24721 | | pus-eng | flores101-devtest | 0.49556 | 22.7 | 1012 | 24721 | | pus-fra | flores101-devtest | 0.45248 | 17.8 | 1012 | 28343 | | tgk-eng | flores101-devtest | 0.53630 | 25.4 | 1012 | 24721 | | tgk-fra | flores101-devtest | 0.49084 | 21.0 | 1012 | 28343 | | tgk-spa | flores101-devtest | 0.43524 | 15.5 | 1012 | 29199 | | ckb-deu | flores200-devtest | 0.40369 | 11.7 | 1012 | 25094 | | ckb-eng | flores200-devtest | 0.48447 | 21.5 | 1012 | 24721 | | ckb-fra | flores200-devtest | 0.44026 | 17.1 | 1012 | 28343 | | ckb-por | flores200-devtest | 0.43192 | 16.4 | 1012 | 26519 | | pes-deu | flores200-devtest | 0.51542 | 21.5 | 1012 | 25094 | | pes-eng | flores200-devtest | 0.61372 | 34.9 | 1012 | 24721 | | pes-fra | flores200-devtest | 0.56347 | 29.2 | 1012 | 28343 | | pes-por | flores200-devtest | 0.55676 | 28.5 | 1012 | 26519 | | pes-spa | flores200-devtest | 0.48334 | 19.8 | 1012 | 29199 | | prs-deu | flores200-devtest | 0.50562 | 21.2 | 1012 | 25094 | | prs-eng | flores200-devtest | 0.60716 | 35.1 | 1012 | 24721 | | prs-fra | flores200-devtest | 0.54769 | 27.8 | 1012 | 28343 | | prs-por | flores200-devtest | 0.54073 | 27.2 | 1012 | 26519 | | prs-spa | flores200-devtest | 0.46850 | 18.6 | 1012 | 29199 | | tgk-deu | flores200-devtest | 0.43115 | 14.2 | 1012 | 25094 | | tgk-eng | flores200-devtest | 0.53705 | 25.6 | 1012 | 24721 | | tgk-fra | flores200-devtest | 0.48902 | 20.7 | 1012 | 28343 | | tgk-por | flores200-devtest | 0.48519 | 20.7 | 1012 | 26519 | | tgk-spa | flores200-devtest | 0.43563 | 15.7 | 1012 | 29199 | | fas-deu | ntrex128 | 0.47408 | 16.7 | 1997 | 48761 | | fas-eng | ntrex128 | 0.55350 | 26.4 | 1997 | 47673 | | fas-fra | ntrex128 | 0.50311 | 22.1 | 1997 | 53481 | | fas-por | ntrex128 | 0.48005 | 19.1 | 1997 | 51631 | | fas-spa | ntrex128 | 0.50973 | 23.6 | 1997 | 54107 | | prs-deu | ntrex128 | 0.45191 | 14.9 | 1997 | 48761 | | prs-eng | ntrex128 | 0.54761 | 26.6 | 1997 | 47673 | | prs-fra | ntrex128 | 0.47819 | 19.9 | 1997 | 53481 | | prs-por | ntrex128 | 0.46241 | 17.4 | 1997 | 51631 | | prs-spa | ntrex128 | 0.48712 | 21.4 | 1997 | 54107 | | pus-eng | ntrex128 | 0.43901 | 17.4 | 1997 | 47673 | | pus-spa | ntrex128 | 0.40812 | 14.1 | 1997 | 54107 | | tgk_Cyrl-eng | ntrex128 | 0.46839 | 18.6 | 1997 | 47673 | | tgk_Cyrl-fra | ntrex128 | 0.42569 | 15.1 | 1997 | 53481 | | tgk_Cyrl-por | ntrex128 | 0.41632 | 13.7 | 1997 | 51631 | | tgk_Cyrl-spa | ntrex128 | 0.43763 | 16.8 | 1997 | 54107 | | ckb-eng | tico19-test | 0.61905 | 40.1 | 2100 | 56315 | | ckb-fra | tico19-test | 0.45070 | 19.7 | 2100 | 64661 | | ckb-por | tico19-test | 0.49617 | 22.9 | 2100 | 62729 | | ckb-spa | tico19-test | 0.50543 | 24.9 | 2100 | 66563 | | fas-eng | tico19-test | 0.64016 | 37.3 | 2100 | 56315 | | fas-fra | tico19-test | 0.53319 | 26.1 | 2100 | 64661 | | fas-por | tico19-test | 0.58008 | 30.6 | 2100 | 62729 | | fas-spa | tico19-test | 0.59239 | 33.3 | 2100 | 66563 | | prs-eng | tico19-test | 0.61702 | 34.8 | 2100 | 56824 | | prs-fra | tico19-test | 0.51218 | 24.0 | 2100 | 64661 | | prs-por | tico19-test | 0.55888 | 28.6 | 2100 | 62729 | | prs-spa | tico19-test | 0.57494 | 31.1 | 2100 | 66563 | | pus-eng | tico19-test | 0.57586 | 32.1 | 2100 | 56315 | | pus-fra | tico19-test | 0.46091 | 19.2 | 2100 | 64661 | | pus-por | tico19-test | 0.51033 | 24.1 | 2100 | 62729 | | pus-spa | tico19-test | 0.51857 | 25.9 | 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 11:54:09 EEST 2024 * port machine: LM0-400-22516.local