tiedeman's picture
Initial commit
aec1379
metadata
library_name: transformers
language:
  - bru
  - cmo
  - de
  - en
  - es
  - fr
  - hoc
  - jun
  - kha
  - km
  - kxm
  - mnw
  - ngt
  - pt
  - sat
  - vi
  - wbm
tags:
  - translation
  - opus-mt-tc-bible
license: apache-2.0
model-index:
  - name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav
    results:
      - task:
          name: Translation deu-vie
          type: translation
          args: deu-vie
        dataset:
          name: flores200-devtest
          type: flores200-devtest
          args: deu-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 34
          - name: chr-F
            type: chrf
            value: 0.53671
      - task:
          name: Translation eng-vie
          type: translation
          args: eng-vie
        dataset:
          name: flores200-devtest
          type: flores200-devtest
          args: eng-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 42.4
          - name: chr-F
            type: chrf
            value: 0.59842
      - task:
          name: Translation fra-vie
          type: translation
          args: fra-vie
        dataset:
          name: flores200-devtest
          type: flores200-devtest
          args: fra-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 34.6
          - name: chr-F
            type: chrf
            value: 0.54101
      - task:
          name: Translation por-vie
          type: translation
          args: por-vie
        dataset:
          name: flores200-devtest
          type: flores200-devtest
          args: por-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 36.1
          - name: chr-F
            type: chrf
            value: 0.5497
      - task:
          name: Translation spa-vie
          type: translation
          args: spa-vie
        dataset:
          name: flores200-devtest
          type: flores200-devtest
          args: spa-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 28.1
          - name: chr-F
            type: chrf
            value: 0.50025
      - task:
          name: Translation deu-vie
          type: translation
          args: deu-vie
        dataset:
          name: flores101-devtest
          type: flores_101
          args: deu vie devtest
        metrics:
          - name: BLEU
            type: bleu
            value: 33.8
          - name: chr-F
            type: chrf
            value: 0.53381
      - task:
          name: Translation eng-vie
          type: translation
          args: eng-vie
        dataset:
          name: flores101-devtest
          type: flores_101
          args: eng vie devtest
        metrics:
          - name: BLEU
            type: bleu
            value: 42.1
          - name: chr-F
            type: chrf
            value: 0.59621
      - task:
          name: Translation por-vie
          type: translation
          args: por-vie
        dataset:
          name: flores101-devtest
          type: flores_101
          args: por vie devtest
        metrics:
          - name: BLEU
            type: bleu
            value: 36
          - name: chr-F
            type: chrf
            value: 0.54919
      - task:
          name: Translation spa-vie
          type: translation
          args: spa-vie
        dataset:
          name: flores101-devtest
          type: flores_101
          args: spa vie devtest
        metrics:
          - name: BLEU
            type: bleu
            value: 27.8
          - name: chr-F
            type: chrf
            value: 0.49921
      - task:
          name: Translation deu-vie
          type: translation
          args: deu-vie
        dataset:
          name: ntrex128
          type: ntrex128
          args: deu-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 31.4
          - name: chr-F
            type: chrf
            value: 0.52124
      - task:
          name: Translation fra-vie
          type: translation
          args: fra-vie
        dataset:
          name: ntrex128
          type: ntrex128
          args: fra-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 31.8
          - name: chr-F
            type: chrf
            value: 0.52044
      - task:
          name: Translation por-vie
          type: translation
          args: por-vie
        dataset:
          name: ntrex128
          type: ntrex128
          args: por-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 33.3
          - name: chr-F
            type: chrf
            value: 0.5306
      - task:
          name: Translation spa-vie
          type: translation
          args: spa-vie
        dataset:
          name: ntrex128
          type: ntrex128
          args: spa-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 33.4
          - name: chr-F
            type: chrf
            value: 0.53293
      - task:
          name: Translation deu-vie
          type: translation
          args: deu-vie
        dataset:
          name: tatoeba-test-v2021-08-07
          type: tatoeba_mt
          args: deu-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 25.6
          - name: chr-F
            type: chrf
            value: 0.45795
      - task:
          name: Translation eng-vie
          type: translation
          args: eng-vie
        dataset:
          name: tatoeba-test-v2021-08-07
          type: tatoeba_mt
          args: eng-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 39.4
          - name: chr-F
            type: chrf
            value: 0.56461
      - task:
          name: Translation fra-vie
          type: translation
          args: fra-vie
        dataset:
          name: tatoeba-test-v2021-08-07
          type: tatoeba_mt
          args: fra-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 35.2
          - name: chr-F
            type: chrf
            value: 0.52806
      - 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: 22.9
          - name: chr-F
            type: chrf
            value: 0.40649
      - task:
          name: Translation spa-vie
          type: translation
          args: spa-vie
        dataset:
          name: tatoeba-test-v2021-08-07
          type: tatoeba_mt
          args: spa-vie
        metrics:
          - name: BLEU
            type: bleu
            value: 34.2
          - name: chr-F
            type: chrf
            value: 0.52131

opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav

Table of Contents

Model Details

Neural machine translation model for translating from unknown (deu+eng+fra+por+spa) to Austro-Asiatic languages (aav).

This model is part of the OPUS-MT project, 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, 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 and training pipelines use the procedures of OPUS-MT-train. Model Description:

  • Developed by: Language Technology Research Group at the University of Helsinki
  • Model Type: Translation (transformer-big)
  • Release: 2024-05-29
  • License: Apache-2.0
  • Language(s):
    • Source Language(s): deu eng fra por spa
    • Target Language(s): bru cmo hoc jun kha khm kxm mnw ngt sat vie wbm
    • Valid Target Language Labels: >>aem<< >>alk<< >>aml<< >>asr<< >>bbh<< >>bdq<< >>bfw<< >>bgk<< >>bgl<< >>bix<< >>biy<< >>blr<< >>brb<< >>bru<< >>brv<< >>btq<< >>caq<< >>cbn<< >>cdz<< >>cma<< >>cmo<< >>cog<< >>crv<< >>crw<< >>cua<< >>cwg<< >>dnu<< >>ekl<< >>gaq<< >>gbj<< >>hal<< >>hld<< >>hnu<< >>hoc<< >>hoc_Wara<< >>hre<< >>huo<< >>irr<< >>jah<< >>jeh<< >>jhi<< >>jun<< >>juy<< >>kdt<< >>kfp<< >>kfq<< >>kha<< >>khf<< >>khm<< >>khr<< >>kjg<< >>kjm<< >>knq<< >>kns<< >>kpm<< >>krr<< >>krv<< >>ksz<< >>kta<< >>ktv<< >>kuf<< >>kxm<< >>kxy<< >>lbn<< >>lbo<< >>lcp<< >>lnh<< >>lwl<< >>lyg<< >>mef<< >>mhe<< >>mjx<< >>mlf<< >>mmj<< >>mml<< >>mng<< >>mnn<< >>mnq<< >>mnw<< >>moo<< >>mqt<< >>mra<< >>mtq<< >>mzt<< >>ncb<< >>ncq<< >>nev<< >>ngt<< >>ngt_Latn<< >>nik<< >>nuo<< >>nyl<< >>omx<< >>oog<< >>oyb<< >>pac<< >>pbv<< >>pcb<< >>pce<< >>pcj<< >>phg<< >>pkt<< >>pll<< >>ply<< >>pnx<< >>prk<< >>prt<< >>puo<< >>rbb<< >>ren<< >>ril<< >>rka<< >>rmx<< >>sat<< >>sat_Latn<< >>sbo<< >>scb<< >>scq<< >>sct<< >>sea<< >>sed<< >>sii<< >>smu<< >>spu<< >>sqq<< >>srb<< >>ssm<< >>sss<< >>stg<< >>sti<< >>stt<< >>stu<< >>syo<< >>sza<< >>szc<< >>tdf<< >>tdr<< >>tea<< >>tef<< >>thm<< >>tkz<< >>tlq<< >>tmo<< >>tnz<< >>tou<< >>tpu<< >>trd<< >>tth<< >>tto<< >>tyh<< >>unr<< >>uuu<< >>vie<< >>vwa<< >>wbm<< >>xao<< >>xkk<< >>xnh<< >>xxx<< >>yin<< >>zng<<
  • Original Model: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.zip
  • Resources for more information:

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. >>bru<<

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) and Bender et al. (2021)).

How to Get Started With the Model

A short example code:

from transformers import MarianMTModel, MarianTokenizer

src_text = [
    ">>khm<< Der Junge wirft einen Stein.",
    ">>vie<< ΒΏY tΓΊ?"
]

model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav"
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) )

# expected output:
#     αž€αŸ’αž˜αŸαž„αž”αŸ’αžšαž»αžŸ αž“αŸ„αŸ‡ αž™αž€ αžŠαž»αŸ† αžαŸ’αž˜ αž‚αž”αŸ‹ αŸ”
#     Còn anh thì sao?

You can also use OPUS-MT models with the transformers pipelines, for example:

from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-aav")
print(pipe(">>khm<< Der Junge wirft einen Stein."))

# expected output: αž€αŸ’αž˜αŸαž„αž”αŸ’αžšαž»αžŸ αž“αŸ„αŸ‡ αž™αž€ αžŠαž»αŸ† αžαŸ’αž˜ αž‚αž”αŸ‹ αŸ”

Training

Evaluation

langpair testset chr-F BLEU #sent #words
deu-vie tatoeba-test-v2021-08-07 0.45795 25.6 400 3768
eng-hoc tatoeba-test-v2021-08-07 6.438 0.2 660 2591
eng-kha tatoeba-test-v2021-08-07 5.741 0.0 1314 9269
eng-vie tatoeba-test-v2021-08-07 0.56461 39.4 2500 24427
fra-vie tatoeba-test-v2021-08-07 0.52806 35.2 1299 13219
spa-vie tatoeba-test-v2021-08-07 0.52131 34.2 594 4740
deu-vie flores101-devtest 0.53381 33.8 1012 33331
eng-khm flores101-devtest 0.42302 1.3 1012 7006
eng-vie flores101-devtest 0.59621 42.1 1012 33331
fra-khm flores101-devtest 0.40042 2.2 1012 7006
por-khm flores101-devtest 0.40585 2.1 1012 7006
por-vie flores101-devtest 0.54919 36.0 1012 33331
spa-vie flores101-devtest 0.49921 27.8 1012 33331
deu-vie flores200-devtest 0.53671 34.0 1012 33331
eng-khm flores200-devtest 0.42148 1.3 1012 7006
eng-vie flores200-devtest 0.59842 42.4 1012 33331
fra-vie flores200-devtest 0.54101 34.6 1012 33331
por-khm flores200-devtest 0.40832 1.9 1012 7006
por-vie flores200-devtest 0.54970 36.1 1012 33331
spa-vie flores200-devtest 0.50025 28.1 1012 33331
deu-khm ntrex128 0.44903 3.5 1997 15866
deu-vie ntrex128 0.52124 31.4 1997 64655
eng-khm ntrex128 0.50494 1.6 1997 15866
eng-vie ntrex128 3.831 0.0 1997 64655
fra-khm ntrex128 0.43841 2.4 1997 15866
fra-vie ntrex128 0.52044 31.8 1997 64655
por-khm ntrex128 0.46655 2.5 1997 15866
por-vie ntrex128 0.53060 33.3 1997 64655
spa-khm ntrex128 0.46443 2.7 1997 15866
spa-vie ntrex128 0.53293 33.4 1997 64655
eng-khm tico19-test 0.47806 2.5 2100 15810
fra-khm tico19-test 3.268 1.0 2100 15810
por-khm tico19-test 3.900 1.1 2100 15810
spa-khm tico19-test 3.784 1.0 2100 15810

Citation Information

@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, 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, Finland, and the EuroHPC supercomputer LUMI.

Model conversion info

  • transformers version: 4.45.1
  • OPUS-MT git hash: 0882077
  • port time: Tue Oct 8 08:57:20 EEST 2024
  • port machine: LM0-400-22516.local