Edit model card

opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh

Table of Contents

Model Details

Neural machine translation model for translating from unknown (deu+eng+fra+por+spa) to Mon-Khmer languages (mkh).

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: 2024-05-30
  • License: Apache-2.0
  • Language(s):
    • Source Language(s): deu eng fra por spa
    • Target Language(s): bru cmo kha khm kxm mnw ngt vie wbm
    • Valid Target Language Labels: >>aem<< >>alk<< >>aml<< >>bbh<< >>bdq<< >>bgk<< >>bgl<< >>blr<< >>brb<< >>bru<< >>brv<< >>btq<< >>caq<< >>cbn<< >>cma<< >>cmo<< >>cog<< >>crv<< >>crw<< >>cua<< >>cwg<< >>dnu<< >>hal<< >>hld<< >>hnu<< >>hre<< >>huo<< >>jah<< >>jeh<< >>jhi<< >>kdt<< >>kha<< >>khf<< >>khm<< >>kjg<< >>kjm<< >>knq<< >>kns<< >>kpm<< >>krr<< >>krv<< >>kta<< >>ktv<< >>kuf<< >>kxm<< >>kxy<< >>lbn<< >>lbo<< >>lcp<< >>lnh<< >>lwl<< >>lyg<< >>mef<< >>mhe<< >>mlf<< >>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<< >>phg<< >>pkt<< >>pll<< >>ply<< >>pnx<< >>prk<< >>prt<< >>puo<< >>rbb<< >>ren<< >>ril<< >>rka<< >>rmx<< >>sbo<< >>scb<< >>scq<< >>sct<< >>sea<< >>sed<< >>sii<< >>smu<< >>spu<< >>sqq<< >>ssm<< >>sss<< >>stg<< >>sti<< >>stt<< >>stu<< >>syo<< >>sza<< >>szc<< >>tdf<< >>tdr<< >>tea<< >>tef<< >>thm<< >>tkz<< >>tlq<< >>tmo<< >>tnz<< >>tou<< >>tpu<< >>tth<< >>tto<< >>tyh<< >>uuu<< >>vie<< >>vwa<< >>wbm<< >>xao<< >>xkk<< >>xnh<< >>xxx<< >>yin<< >>zng<<
  • Original Model: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.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 = [
    ">>bru<< Replace this with text in an accepted source language.",
    ">>wbm<< This is the second sentence."
]

model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh"
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:

from transformers import pipeline
pipe = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh")
print(pipe(">>bru<< Replace this with text in an accepted source language."))

Training

Evaluation

langpair testset chr-F BLEU #sent #words
deu-vie tatoeba-test-v2021-08-07 0.45222 25.3 400 3768
eng-kha tatoeba-test-v2021-08-07 9.076 0.4 1314 9269
eng-vie tatoeba-test-v2021-08-07 0.56413 39.0 2500 24427
fra-vie tatoeba-test-v2021-08-07 0.53078 35.6 1299 13219
spa-vie tatoeba-test-v2021-08-07 0.51783 34.0 594 4740
deu-vie flores101-devtest 0.53623 33.9 1012 33331
eng-khm flores101-devtest 0.42022 1.4 1012 7006
eng-vie flores101-devtest 0.59986 42.7 1012 33331
por-vie flores101-devtest 0.54819 35.7 1012 33331
deu-vie flores200-devtest 0.53535 33.9 1012 33331
eng-khm flores200-devtest 0.41987 1.3 1012 7006
eng-vie flores200-devtest 0.60021 42.6 1012 33331
fra-khm flores200-devtest 0.40241 2.3 1012 7006
fra-vie flores200-devtest 0.54168 34.6 1012 33331
por-khm flores200-devtest 0.41582 2.3 1012 7006
por-vie flores200-devtest 0.55046 35.9 1012 33331
spa-vie flores200-devtest 0.50262 28.1 1012 33331
deu-khm ntrex128 0.44917 3.2 1997 15866
deu-vie ntrex128 0.51996 31.2 1997 64655
eng-khm ntrex128 0.50215 1.6 1997 15866
eng-vie ntrex128 0.60050 42.7 1997 64655
fra-khm ntrex128 0.44024 2.3 1997 15866
fra-vie ntrex128 0.51988 31.7 1997 64655
por-khm ntrex128 0.46752 2.4 1997 15866
por-vie ntrex128 0.52931 33.3 1997 64655
spa-khm ntrex128 0.46166 2.5 1997 15866
spa-vie ntrex128 0.53347 33.1 1997 64655
eng-khm tico19-test 0.54267 3.4 2100 15810
fra-khm tico19-test 0.45333 4.8 2100 15810
por-khm tico19-test 0.52339 6.8 2100 15810
spa-khm tico19-test 0.51848 6.8 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 10:19:52 EEST 2024
  • port machine: LM0-400-22516.local
Downloads last month
7
Safetensors
Model size
235M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Collection including Helsinki-NLP/opus-mt-tc-bible-big-deu_eng_fra_por_spa-mkh

Evaluation results