--- library_name: transformers language: - da - de - en - es - fo - fr - is - nb - nn - no - non - pt - sv tags: - translation - opus-mt-tc-bible license: apache-2.0 model-index: - name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-gmq results: - task: name: Translation deu-dan type: translation args: deu-dan dataset: name: flores200-devtest type: flores200-devtest args: deu-dan metrics: - name: BLEU type: bleu value: 35.1 - name: chr-F type: chrf value: 0.62152 - task: name: Translation deu-fao type: translation args: deu-fao dataset: name: flores200-devtest type: flores200-devtest args: deu-fao metrics: - name: BLEU type: bleu value: 11.5 - name: chr-F type: chrf value: 0.33611 - task: name: Translation deu-isl type: translation args: deu-isl dataset: name: flores200-devtest type: flores200-devtest args: deu-isl metrics: - name: BLEU type: bleu value: 19.1 - name: chr-F type: chrf value: 0.48648 - task: name: Translation deu-nno type: translation args: deu-nno dataset: name: flores200-devtest type: flores200-devtest args: deu-nno metrics: - name: BLEU type: bleu value: 24.0 - name: chr-F type: chrf value: 0.53530 - task: name: Translation deu-nob type: translation args: deu-nob dataset: name: flores200-devtest type: flores200-devtest args: deu-nob metrics: - name: BLEU type: bleu value: 25.1 - name: chr-F type: chrf value: 0.55748 - task: name: Translation deu-swe type: translation args: deu-swe dataset: name: flores200-devtest type: flores200-devtest args: deu-swe metrics: - name: BLEU type: bleu value: 34.2 - name: chr-F type: chrf value: 0.62138 - task: name: Translation eng-dan type: translation args: eng-dan dataset: name: flores200-devtest type: flores200-devtest args: eng-dan metrics: - name: BLEU type: bleu value: 47.0 - name: chr-F type: chrf value: 0.70321 - task: name: Translation eng-fao type: translation args: eng-fao dataset: name: flores200-devtest type: flores200-devtest args: eng-fao metrics: - name: BLEU type: bleu value: 14.1 - name: chr-F type: chrf value: 0.35857 - task: name: Translation eng-isl type: translation args: eng-isl dataset: name: flores200-devtest type: flores200-devtest args: eng-isl metrics: - name: BLEU type: bleu value: 24.4 - name: chr-F type: chrf value: 0.52585 - task: name: Translation eng-nno type: translation args: eng-nno dataset: name: flores200-devtest type: flores200-devtest args: eng-nno metrics: - name: BLEU type: bleu value: 33.8 - name: chr-F type: chrf value: 0.61372 - task: name: Translation eng-nob type: translation args: eng-nob dataset: name: flores200-devtest type: flores200-devtest args: eng-nob metrics: - name: BLEU type: bleu value: 34.4 - name: chr-F type: chrf value: 0.62508 - task: name: Translation eng-swe type: translation args: eng-swe dataset: name: flores200-devtest type: flores200-devtest args: eng-swe metrics: - name: BLEU type: bleu value: 46.0 - name: chr-F type: chrf value: 0.69703 - task: name: Translation fra-dan type: translation args: fra-dan dataset: name: flores200-devtest type: flores200-devtest args: fra-dan metrics: - name: BLEU type: bleu value: 34.1 - name: chr-F type: chrf value: 0.61025 - task: name: Translation fra-isl type: translation args: fra-isl dataset: name: flores200-devtest type: flores200-devtest args: fra-isl metrics: - name: BLEU type: bleu value: 18.8 - name: chr-F type: chrf value: 0.48273 - task: name: Translation fra-nno type: translation args: fra-nno dataset: name: flores200-devtest type: flores200-devtest args: fra-nno metrics: - name: BLEU type: bleu value: 24.3 - name: chr-F type: chrf value: 0.53032 - task: name: Translation fra-nob type: translation args: fra-nob dataset: name: flores200-devtest type: flores200-devtest args: fra-nob metrics: - name: BLEU type: bleu value: 25.0 - name: chr-F type: chrf value: 0.54933 - task: name: Translation fra-swe type: translation args: fra-swe dataset: name: flores200-devtest type: flores200-devtest args: fra-swe metrics: - name: BLEU type: bleu value: 32.8 - name: chr-F type: chrf value: 0.60612 - task: name: Translation por-dan type: translation args: por-dan dataset: name: flores200-devtest type: flores200-devtest args: por-dan metrics: - name: BLEU type: bleu value: 36.2 - name: chr-F type: chrf value: 0.62221 - task: name: Translation por-fao type: translation args: por-fao dataset: name: flores200-devtest type: flores200-devtest args: por-fao metrics: - name: BLEU type: bleu value: 11.5 - name: chr-F type: chrf value: 0.33159 - task: name: Translation por-isl type: translation args: por-isl dataset: name: flores200-devtest type: flores200-devtest args: por-isl metrics: - name: BLEU type: bleu value: 19.6 - name: chr-F type: chrf value: 0.48357 - task: name: Translation por-nno type: translation args: por-nno dataset: name: flores200-devtest type: flores200-devtest args: por-nno metrics: - name: BLEU type: bleu value: 26.3 - name: chr-F type: chrf value: 0.54369 - task: name: Translation por-nob type: translation args: por-nob dataset: name: flores200-devtest type: flores200-devtest args: por-nob metrics: - name: BLEU type: bleu value: 26.4 - name: chr-F type: chrf value: 0.56054 - task: name: Translation por-swe type: translation args: por-swe dataset: name: flores200-devtest type: flores200-devtest args: por-swe metrics: - name: BLEU type: bleu value: 34.1 - name: chr-F type: chrf value: 0.61388 - task: name: Translation spa-dan type: translation args: spa-dan dataset: name: flores200-devtest type: flores200-devtest args: spa-dan metrics: - name: BLEU type: bleu value: 24.7 - name: chr-F type: chrf value: 0.55091 - task: name: Translation spa-isl type: translation args: spa-isl dataset: name: flores200-devtest type: flores200-devtest args: spa-isl metrics: - name: BLEU type: bleu value: 14.2 - name: chr-F type: chrf value: 0.44469 - task: name: Translation spa-nno type: translation args: spa-nno dataset: name: flores200-devtest type: flores200-devtest args: spa-nno metrics: - name: BLEU type: bleu value: 18.6 - name: chr-F type: chrf value: 0.48898 - task: name: Translation spa-nob type: translation args: spa-nob dataset: name: flores200-devtest type: flores200-devtest args: spa-nob metrics: - name: BLEU type: bleu value: 18.8 - name: chr-F type: chrf value: 0.50901 - task: name: Translation spa-swe type: translation args: spa-swe dataset: name: flores200-devtest type: flores200-devtest args: spa-swe metrics: - name: BLEU type: bleu value: 22.7 - name: chr-F type: chrf value: 0.54182 - task: name: Translation deu-dan type: translation args: deu-dan dataset: name: flores101-devtest type: flores_101 args: deu dan devtest metrics: - name: BLEU type: bleu value: 34.8 - name: chr-F type: chrf value: 0.62006 - task: name: Translation deu-isl type: translation args: deu-isl dataset: name: flores101-devtest type: flores_101 args: deu isl devtest metrics: - name: BLEU type: bleu value: 18.8 - name: chr-F type: chrf value: 0.48236 - task: name: Translation deu-swe type: translation args: deu-swe dataset: name: flores101-devtest type: flores_101 args: deu swe devtest metrics: - name: BLEU type: bleu value: 33.7 - name: chr-F type: chrf value: 0.61778 - task: name: Translation eng-swe type: translation args: eng-swe dataset: name: flores101-devtest type: flores_101 args: eng swe devtest metrics: - name: BLEU type: bleu value: 45.5 - name: chr-F type: chrf value: 0.69435 - task: name: Translation fra-dan type: translation args: fra-dan dataset: name: flores101-devtest type: flores_101 args: fra dan devtest metrics: - name: BLEU type: bleu value: 34.0 - name: chr-F type: chrf value: 0.61019 - task: name: Translation fra-isl type: translation args: fra-isl dataset: name: flores101-devtest type: flores_101 args: fra isl devtest metrics: - name: BLEU type: bleu value: 18.1 - name: chr-F type: chrf value: 0.47647 - task: name: Translation fra-swe type: translation args: fra-swe dataset: name: flores101-devtest type: flores_101 args: fra swe devtest metrics: - name: BLEU type: bleu value: 32.2 - name: chr-F type: chrf value: 0.60354 - task: name: Translation por-isl type: translation args: por-isl dataset: name: flores101-devtest type: flores_101 args: por isl devtest metrics: - name: BLEU type: bleu value: 19.1 - name: chr-F type: chrf value: 0.47937 - task: name: Translation por-swe type: translation args: por-swe dataset: name: flores101-devtest type: flores_101 args: por swe devtest metrics: - name: BLEU type: bleu value: 33.1 - name: chr-F type: chrf value: 0.60857 - task: name: Translation spa-dan type: translation args: spa-dan dataset: name: flores101-devtest type: flores_101 args: spa dan devtest metrics: - name: BLEU type: bleu value: 24.4 - name: chr-F type: chrf value: 0.54890 - task: name: Translation spa-nob type: translation args: spa-nob dataset: name: flores101-devtest type: flores_101 args: spa nob devtest metrics: - name: BLEU type: bleu value: 18.3 - name: chr-F type: chrf value: 0.50610 - task: name: Translation spa-swe type: translation args: spa-swe dataset: name: flores101-devtest type: flores_101 args: spa swe devtest metrics: - name: BLEU type: bleu value: 22.4 - name: chr-F type: chrf value: 0.54011 - task: name: Translation deu-dan type: translation args: deu-dan dataset: name: ntrex128 type: ntrex128 args: deu-dan metrics: - name: BLEU type: bleu value: 29.1 - name: chr-F type: chrf value: 0.56412 - task: name: Translation deu-fao type: translation args: deu-fao dataset: name: ntrex128 type: ntrex128 args: deu-fao metrics: - name: BLEU type: bleu value: 12.5 - name: chr-F type: chrf value: 0.35495 - task: name: Translation deu-isl type: translation args: deu-isl dataset: name: ntrex128 type: ntrex128 args: deu-isl metrics: - name: BLEU type: bleu value: 18.8 - name: chr-F type: chrf value: 0.48309 - task: name: Translation deu-nno type: translation args: deu-nno dataset: name: ntrex128 type: ntrex128 args: deu-nno metrics: - name: BLEU type: bleu value: 22.0 - name: chr-F type: chrf value: 0.51535 - task: name: Translation deu-nob type: translation args: deu-nob dataset: name: ntrex128 type: ntrex128 args: deu-nob metrics: - name: BLEU type: bleu value: 27.6 - name: chr-F type: chrf value: 0.56152 - task: name: Translation deu-swe type: translation args: deu-swe dataset: name: ntrex128 type: ntrex128 args: deu-swe metrics: - name: BLEU type: bleu value: 29.6 - name: chr-F type: chrf value: 0.58061 - task: name: Translation eng-dan type: translation args: eng-dan dataset: name: ntrex128 type: ntrex128 args: eng-dan metrics: - name: BLEU type: bleu value: 37.6 - name: chr-F type: chrf value: 0.61894 - task: name: Translation eng-fao type: translation args: eng-fao dataset: name: ntrex128 type: ntrex128 args: eng-fao metrics: - name: BLEU type: bleu value: 15.9 - name: chr-F type: chrf value: 0.38410 - task: name: Translation eng-isl type: translation args: eng-isl dataset: name: ntrex128 type: ntrex128 args: eng-isl metrics: - name: BLEU type: bleu value: 23.9 - name: chr-F type: chrf value: 0.52027 - task: name: Translation eng-nno type: translation args: eng-nno dataset: name: ntrex128 type: ntrex128 args: eng-nno metrics: - name: BLEU type: bleu value: 34.0 - name: chr-F type: chrf value: 0.60754 - task: name: Translation eng-nob type: translation args: eng-nob dataset: name: ntrex128 type: ntrex128 args: eng-nob metrics: - name: BLEU type: bleu value: 36.9 - name: chr-F type: chrf value: 0.62327 - task: name: Translation eng-swe type: translation args: eng-swe dataset: name: ntrex128 type: ntrex128 args: eng-swe metrics: - name: BLEU type: bleu value: 41.3 - name: chr-F type: chrf value: 0.66129 - task: name: Translation fra-dan type: translation args: fra-dan dataset: name: ntrex128 type: ntrex128 args: fra-dan metrics: - name: BLEU type: bleu value: 27.1 - name: chr-F type: chrf value: 0.54102 - task: name: Translation fra-fao type: translation args: fra-fao dataset: name: ntrex128 type: ntrex128 args: fra-fao metrics: - name: BLEU type: bleu value: 10.8 - name: chr-F type: chrf value: 0.32337 - task: name: Translation fra-isl type: translation args: fra-isl dataset: name: ntrex128 type: ntrex128 args: fra-isl metrics: - name: BLEU type: bleu value: 18.4 - name: chr-F type: chrf value: 0.47296 - task: name: Translation fra-nno type: translation args: fra-nno dataset: name: ntrex128 type: ntrex128 args: fra-nno metrics: - name: BLEU type: bleu value: 21.6 - name: chr-F type: chrf value: 0.50532 - task: name: Translation fra-nob type: translation args: fra-nob dataset: name: ntrex128 type: ntrex128 args: fra-nob metrics: - name: BLEU type: bleu value: 25.7 - name: chr-F type: chrf value: 0.54026 - task: name: Translation fra-swe type: translation args: fra-swe dataset: name: ntrex128 type: ntrex128 args: fra-swe metrics: - name: BLEU type: bleu value: 27.9 - name: chr-F type: chrf value: 0.56278 - task: name: Translation por-dan type: translation args: por-dan dataset: name: ntrex128 type: ntrex128 args: por-dan metrics: - name: BLEU type: bleu value: 30.0 - name: chr-F type: chrf value: 0.56288 - task: name: Translation por-fao type: translation args: por-fao dataset: name: ntrex128 type: ntrex128 args: por-fao metrics: - name: BLEU type: bleu value: 12.7 - name: chr-F type: chrf value: 0.35059 - task: name: Translation por-isl type: translation args: por-isl dataset: name: ntrex128 type: ntrex128 args: por-isl metrics: - name: BLEU type: bleu value: 17.8 - name: chr-F type: chrf value: 0.47577 - task: name: Translation por-nno type: translation args: por-nno dataset: name: ntrex128 type: ntrex128 args: por-nno metrics: - name: BLEU type: bleu value: 23.0 - name: chr-F type: chrf value: 0.52158 - task: name: Translation por-nob type: translation args: por-nob dataset: name: ntrex128 type: ntrex128 args: por-nob metrics: - name: BLEU type: bleu value: 27.4 - name: chr-F type: chrf value: 0.55788 - task: name: Translation por-swe type: translation args: por-swe dataset: name: ntrex128 type: ntrex128 args: por-swe metrics: - name: BLEU type: bleu value: 29.3 - name: chr-F type: chrf value: 0.57790 - task: name: Translation spa-dan type: translation args: spa-dan dataset: name: ntrex128 type: ntrex128 args: spa-dan metrics: - name: BLEU type: bleu value: 27.5 - name: chr-F type: chrf value: 0.55607 - task: name: Translation spa-fao type: translation args: spa-fao dataset: name: ntrex128 type: ntrex128 args: spa-fao metrics: - name: BLEU type: bleu value: 12.5 - name: chr-F type: chrf value: 0.34781 - task: name: Translation spa-isl type: translation args: spa-isl dataset: name: ntrex128 type: ntrex128 args: spa-isl metrics: - name: BLEU type: bleu value: 18.4 - name: chr-F type: chrf value: 0.48566 - task: name: Translation spa-nno type: translation args: spa-nno dataset: name: ntrex128 type: ntrex128 args: spa-nno metrics: - name: BLEU type: bleu value: 22.2 - name: chr-F type: chrf value: 0.51741 - task: name: Translation spa-nob type: translation args: spa-nob dataset: name: ntrex128 type: ntrex128 args: spa-nob metrics: - name: BLEU type: bleu value: 26.8 - name: chr-F type: chrf value: 0.55824 - task: name: Translation spa-swe type: translation args: spa-swe dataset: name: ntrex128 type: ntrex128 args: spa-swe metrics: - name: BLEU type: bleu value: 28.8 - name: chr-F type: chrf value: 0.57851 - task: name: Translation deu-dan type: translation args: deu-dan dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-dan metrics: - name: BLEU type: bleu value: 57.8 - name: chr-F type: chrf value: 0.74051 - task: name: Translation deu-isl type: translation args: deu-isl dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-isl metrics: - name: BLEU type: bleu value: 31.7 - name: chr-F type: chrf value: 0.61256 - task: name: Translation deu-nob type: translation args: deu-nob dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-nob metrics: - name: BLEU type: bleu value: 52.9 - name: chr-F type: chrf value: 0.71413 - task: name: Translation deu-nor type: translation args: deu-nor dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-nor metrics: - name: BLEU type: bleu value: 52.7 - name: chr-F type: chrf value: 0.71253 - task: name: Translation deu-swe type: translation args: deu-swe dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: deu-swe metrics: - name: BLEU type: bleu value: 58.2 - name: chr-F type: chrf value: 0.72650 - task: name: Translation eng-dan type: translation args: eng-dan dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-dan metrics: - name: BLEU type: bleu value: 60.6 - name: chr-F type: chrf value: 0.74708 - task: name: Translation eng-fao type: translation args: eng-fao dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-fao metrics: - name: BLEU type: bleu value: 29.0 - name: chr-F type: chrf value: 0.48304 - task: name: Translation eng-isl type: translation args: eng-isl dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-isl metrics: - name: BLEU type: bleu value: 33.2 - name: chr-F type: chrf value: 0.58312 - task: name: Translation eng-nno type: translation args: eng-nno dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-nno metrics: - name: BLEU type: bleu value: 42.7 - name: chr-F type: chrf value: 0.62606 - task: name: Translation eng-nob type: translation args: eng-nob dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-nob metrics: - name: BLEU type: bleu value: 57.4 - name: chr-F type: chrf value: 0.72340 - task: name: Translation eng-nor type: translation args: eng-nor dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-nor metrics: - name: BLEU type: bleu value: 56.2 - name: chr-F type: chrf value: 0.71514 - task: name: Translation eng-swe type: translation args: eng-swe dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: eng-swe metrics: - name: BLEU type: bleu value: 60.5 - name: chr-F type: chrf value: 0.73720 - task: name: Translation fra-dan type: translation args: fra-dan dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fra-dan metrics: - name: BLEU type: bleu value: 64.1 - name: chr-F type: chrf value: 0.78018 - task: name: Translation fra-nob type: translation args: fra-nob dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fra-nob metrics: - name: BLEU type: bleu value: 59.1 - name: chr-F type: chrf value: 0.74252 - task: name: Translation fra-nor type: translation args: fra-nor dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fra-nor metrics: - name: BLEU type: bleu value: 60.3 - name: chr-F type: chrf value: 0.74407 - task: name: Translation fra-swe type: translation args: fra-swe dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: fra-swe metrics: - name: BLEU type: bleu value: 62.1 - name: chr-F type: chrf value: 0.75644 - 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: 56.4 - name: chr-F type: chrf value: 0.72858 - task: name: Translation por-dan type: translation args: por-dan dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: por-dan metrics: - name: BLEU type: bleu value: 65.6 - name: chr-F type: chrf value: 0.79528 - task: name: Translation por-nor type: translation args: por-nor dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: por-nor metrics: - name: BLEU type: bleu value: 58.0 - name: chr-F type: chrf value: 0.73559 - task: name: Translation por-swe type: translation args: por-swe dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: por-swe metrics: - name: BLEU type: bleu value: 60.2 - name: chr-F type: chrf value: 0.75566 - task: name: Translation spa-dan type: translation args: spa-dan dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: spa-dan metrics: - name: BLEU type: bleu value: 57.7 - name: chr-F type: chrf value: 0.73310 - task: name: Translation spa-nob type: translation args: spa-nob dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: spa-nob metrics: - name: BLEU type: bleu value: 60.9 - name: chr-F type: chrf value: 0.76501 - task: name: Translation spa-nor type: translation args: spa-nor dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: spa-nor metrics: - name: BLEU type: bleu value: 60.1 - name: chr-F type: chrf value: 0.75815 - task: name: Translation spa-swe type: translation args: spa-swe dataset: name: tatoeba-test-v2021-08-07 type: tatoeba_mt args: spa-swe metrics: - name: BLEU type: bleu value: 60.7 - name: chr-F type: chrf value: 0.74222 - task: name: Translation eng-isl type: translation args: eng-isl dataset: name: newstest2021 type: wmt-2021-news args: eng-isl metrics: - name: BLEU type: bleu value: 21.9 - name: chr-F type: chrf value: 0.51196 --- # opus-mt-tc-bible-big-deu_eng_fra_por_spa-gmq ## 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 North Germanic languages (gmq). 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): dan fao isl nno nob non nor swe - Valid Target Language Labels: >>dan<< >>fao<< >>isl<< >>jut<< >>nno<< >>nob<< >>non<< >>nor<< >>nrn<< >>ovd<< >>rmg<< >>swe<< >>xxx<< - **Original Model**: [opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip](https://object.pouta.csc.fi/Tatoeba-MT-models/deu+eng+fra+por+spa-gmq/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-gmq/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. `>>dan<<` ## 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 = [ ">>dan<< Replace this with text in an accepted source language.", ">>swe<< This is the second sentence." ] model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-gmq" 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-gmq") print(pipe(">>dan<< 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-gmq/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-gmq/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-gmq/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-gmq/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-dan | tatoeba-test-v2021-08-07 | 0.74051 | 57.8 | 9998 | 74644 | | deu-isl | tatoeba-test-v2021-08-07 | 0.61256 | 31.7 | 969 | 5951 | | deu-nob | tatoeba-test-v2021-08-07 | 0.71413 | 52.9 | 3525 | 31978 | | deu-nor | tatoeba-test-v2021-08-07 | 0.71253 | 52.7 | 3651 | 32928 | | deu-swe | tatoeba-test-v2021-08-07 | 0.72650 | 58.2 | 3410 | 22701 | | eng-dan | tatoeba-test-v2021-08-07 | 0.74708 | 60.6 | 10795 | 79385 | | eng-fao | tatoeba-test-v2021-08-07 | 0.48304 | 29.0 | 294 | 1933 | | eng-isl | tatoeba-test-v2021-08-07 | 0.58312 | 33.2 | 2503 | 19023 | | eng-nno | tatoeba-test-v2021-08-07 | 0.62606 | 42.7 | 460 | 3428 | | eng-nob | tatoeba-test-v2021-08-07 | 0.72340 | 57.4 | 4539 | 36119 | | eng-nor | tatoeba-test-v2021-08-07 | 0.71514 | 56.2 | 5000 | 39552 | | eng-swe | tatoeba-test-v2021-08-07 | 0.73720 | 60.5 | 10362 | 68067 | | fra-dan | tatoeba-test-v2021-08-07 | 0.78018 | 64.1 | 1731 | 11312 | | fra-nob | tatoeba-test-v2021-08-07 | 0.74252 | 59.1 | 323 | 2175 | | fra-nor | tatoeba-test-v2021-08-07 | 0.74407 | 60.3 | 477 | 3097 | | fra-swe | tatoeba-test-v2021-08-07 | 0.75644 | 62.1 | 1407 | 9170 | | por-dan | tatoeba-test-v2021-08-07 | 0.79528 | 65.6 | 873 | 5258 | | por-nor | tatoeba-test-v2021-08-07 | 0.73559 | 58.0 | 481 | 4030 | | por-swe | tatoeba-test-v2021-08-07 | 0.75566 | 60.2 | 320 | 1938 | | spa-dan | tatoeba-test-v2021-08-07 | 0.73310 | 57.7 | 5000 | 35937 | | spa-isl | tatoeba-test-v2021-08-07 | 0.52169 | 18.7 | 238 | 1220 | | spa-nob | tatoeba-test-v2021-08-07 | 0.76501 | 60.9 | 885 | 6762 | | spa-nor | tatoeba-test-v2021-08-07 | 0.75815 | 60.1 | 960 | 7217 | | spa-swe | tatoeba-test-v2021-08-07 | 0.74222 | 60.7 | 1351 | 8357 | | deu-dan | flores101-devtest | 0.62006 | 34.8 | 1012 | 24638 | | deu-isl | flores101-devtest | 0.48236 | 18.8 | 1012 | 22834 | | deu-swe | flores101-devtest | 0.61778 | 33.7 | 1012 | 23121 | | eng-swe | flores101-devtest | 0.69435 | 45.5 | 1012 | 23121 | | fra-dan | flores101-devtest | 0.61019 | 34.0 | 1012 | 24638 | | fra-isl | flores101-devtest | 0.47647 | 18.1 | 1012 | 22834 | | fra-swe | flores101-devtest | 0.60354 | 32.2 | 1012 | 23121 | | por-isl | flores101-devtest | 0.47937 | 19.1 | 1012 | 22834 | | por-swe | flores101-devtest | 0.60857 | 33.1 | 1012 | 23121 | | spa-dan | flores101-devtest | 0.54890 | 24.4 | 1012 | 24638 | | spa-nob | flores101-devtest | 0.50610 | 18.3 | 1012 | 23873 | | spa-swe | flores101-devtest | 0.54011 | 22.4 | 1012 | 23121 | | deu-dan | flores200-devtest | 0.62152 | 35.1 | 1012 | 24638 | | deu-isl | flores200-devtest | 0.48648 | 19.1 | 1012 | 22834 | | deu-nno | flores200-devtest | 0.53530 | 24.0 | 1012 | 24316 | | deu-nob | flores200-devtest | 0.55748 | 25.1 | 1012 | 23873 | | deu-swe | flores200-devtest | 0.62138 | 34.2 | 1012 | 23121 | | eng-dan | flores200-devtest | 0.70321 | 47.0 | 1012 | 24638 | | eng-isl | flores200-devtest | 0.52585 | 24.4 | 1012 | 22834 | | eng-nno | flores200-devtest | 0.61372 | 33.8 | 1012 | 24316 | | eng-nob | flores200-devtest | 0.62508 | 34.4 | 1012 | 23873 | | eng-swe | flores200-devtest | 0.69703 | 46.0 | 1012 | 23121 | | fra-dan | flores200-devtest | 0.61025 | 34.1 | 1012 | 24638 | | fra-isl | flores200-devtest | 0.48273 | 18.8 | 1012 | 22834 | | fra-nno | flores200-devtest | 0.53032 | 24.3 | 1012 | 24316 | | fra-nob | flores200-devtest | 0.54933 | 25.0 | 1012 | 23873 | | fra-swe | flores200-devtest | 0.60612 | 32.8 | 1012 | 23121 | | por-dan | flores200-devtest | 0.62221 | 36.2 | 1012 | 24638 | | por-isl | flores200-devtest | 0.48357 | 19.6 | 1012 | 22834 | | por-nno | flores200-devtest | 0.54369 | 26.3 | 1012 | 24316 | | por-nob | flores200-devtest | 0.56054 | 26.4 | 1012 | 23873 | | por-swe | flores200-devtest | 0.61388 | 34.1 | 1012 | 23121 | | spa-dan | flores200-devtest | 0.55091 | 24.7 | 1012 | 24638 | | spa-isl | flores200-devtest | 0.44469 | 14.2 | 1012 | 22834 | | spa-nno | flores200-devtest | 0.48898 | 18.6 | 1012 | 24316 | | spa-nob | flores200-devtest | 0.50901 | 18.8 | 1012 | 23873 | | spa-swe | flores200-devtest | 0.54182 | 22.7 | 1012 | 23121 | | eng-isl | newstest2021 | 0.51196 | 21.9 | 1000 | 25233 | | deu-dan | ntrex128 | 0.56412 | 29.1 | 1997 | 47643 | | deu-isl | ntrex128 | 0.48309 | 18.8 | 1997 | 46643 | | deu-nno | ntrex128 | 0.51535 | 22.0 | 1997 | 46512 | | deu-nob | ntrex128 | 0.56152 | 27.6 | 1997 | 45501 | | deu-swe | ntrex128 | 0.58061 | 29.6 | 1997 | 44889 | | eng-dan | ntrex128 | 0.61894 | 37.6 | 1997 | 47643 | | eng-isl | ntrex128 | 0.52027 | 23.9 | 1997 | 46643 | | eng-nno | ntrex128 | 0.60754 | 34.0 | 1997 | 46512 | | eng-nob | ntrex128 | 0.62327 | 36.9 | 1997 | 45501 | | eng-swe | ntrex128 | 0.66129 | 41.3 | 1997 | 44889 | | fra-dan | ntrex128 | 0.54102 | 27.1 | 1997 | 47643 | | fra-isl | ntrex128 | 0.47296 | 18.4 | 1997 | 46643 | | fra-nno | ntrex128 | 0.50532 | 21.6 | 1997 | 46512 | | fra-nob | ntrex128 | 0.54026 | 25.7 | 1997 | 45501 | | fra-swe | ntrex128 | 0.56278 | 27.9 | 1997 | 44889 | | por-dan | ntrex128 | 0.56288 | 30.0 | 1997 | 47643 | | por-isl | ntrex128 | 0.47577 | 17.8 | 1997 | 46643 | | por-nno | ntrex128 | 0.52158 | 23.0 | 1997 | 46512 | | por-nob | ntrex128 | 0.55788 | 27.4 | 1997 | 45501 | | por-swe | ntrex128 | 0.57790 | 29.3 | 1997 | 44889 | | spa-dan | ntrex128 | 0.55607 | 27.5 | 1997 | 47643 | | spa-isl | ntrex128 | 0.48566 | 18.4 | 1997 | 46643 | | spa-nno | ntrex128 | 0.51741 | 22.2 | 1997 | 46512 | | spa-nob | ntrex128 | 0.55824 | 26.8 | 1997 | 45501 | | spa-swe | ntrex128 | 0.57851 | 28.8 | 1997 | 44889 | ## 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 10:03:29 EEST 2024 * port machine: LM0-400-22516.local