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): lav lit prg sgs
- Valid Target Language Labels: >>lav<< >>lit<< >>ndf<< >>olt<< >>prg<< >>prg_Latn<< >>sgs<< >>svx<< >>sxl<< >>xcu<< >>xgl<< >>xsv<< >>xzm<<
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. >>lav<<

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:

python

from transformers import MarianMTModel, MarianTokenizer

src_text = [
    ">>lav<< Replace this with text in an accepted source language.",
    ">>sgs<< This is the second sentence."
]

model_name = "pytorch-models/opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat"
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-bat")
print(pipe(">>lav<< Replace this with text in an accepted source language."))

Training

Data: opusTCv20230926max50+bt+jhubc (source)
Pre-processing: SentencePiece (spm32k,spm32k)
Model Type: transformer-big
Original MarianNMT Model: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-30.zip
Training Scripts: GitHub Repo

Evaluation

Model scores at the OPUS-MT dashboard
test set translations: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.test.txt
test set scores: opusTCv20230926max50+bt+jhubc_transformer-big_2024-05-29.eval.txt
benchmark results: benchmark_results.txt
benchmark output: benchmark_translations.zip

langpair	testset	chr-F	BLEU	#sent	#words
deu-lit	tatoeba-test-v2021-08-07	0.65379	39.8	1115	7091
eng-lav	tatoeba-test-v2021-08-07	0.68823	46.4	1631	9932
eng-lit	tatoeba-test-v2021-08-07	0.67792	39.8	2528	14942
spa-lit	tatoeba-test-v2021-08-07	0.68133	43.3	454	2352
deu-lav	flores101-devtest	0.54724	24.4	1012	22092
eng-lav	flores101-devtest	0.59955	31.0	1012	22092
eng-lit	flores101-devtest	0.58961	27.2	1012	20695
fra-lav	flores101-devtest	0.54276	24.2	1012	22092
fra-lit	flores101-devtest	0.54665	22.4	1012	20695
spa-lav	flores101-devtest	0.50131	17.8	1012	22092
deu-lit	flores200-devtest	0.54957	22.6	1012	20695
eng-lit	flores200-devtest	0.59338	27.7	1012	20695
fra-lit	flores200-devtest	0.54683	22.3	1012	20695
por-lit	flores200-devtest	0.55033	22.6	1012	20695
spa-lit	flores200-devtest	0.50725	16.9	1012	20695
eng-lav	newstest2017	0.53192	21.5	2001	39392
eng-lit	newstest2019	0.51714	18.3	998	19711
deu-lav	ntrex128	0.47980	16.8	1997	44709
deu-lit	ntrex128	0.50645	17.6	1997	41189
eng-lav	ntrex128	0.51026	20.6	1997	44709
eng-lit	ntrex128	0.54187	21.5	1997	41189
fra-lav	ntrex128	0.45346	15.5	1997	44709
fra-lit	ntrex128	0.48870	16.2	1997	41189
por-lav	ntrex128	0.47809	17.3	1997	44709
por-lit	ntrex128	0.50653	17.5	1997	41189
spa-lav	ntrex128	0.47690	17.1	1997	44709
spa-lit	ntrex128	0.50412	17.1	1997	41189

Citation Information

Publications: Democratizing neural machine translation with OPUS-MT and OPUS-MT – Building open translation services for the World and The Tatoeba Translation Challenge – Realistic Data Sets for Low Resource and Multilingual MT (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, 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 08:59:36 EEST 2024
port machine: LM0-400-22516.local

WindstormLabs/origin-Helsinki-NLP-opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat

opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat

Table of Contents

Model Details