metadata
library_name: transformers
language:
- de
- en
- es
- fr
- lt
- lv
- prg
- pt
- sgs
tags:
- translation
- opus-mt-tc-bible
license: apache-2.0
model-index:
- name: opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat
results:
- task:
name: Translation deu-lit
type: translation
args: deu-lit
dataset:
name: flores200-devtest
type: flores200-devtest
args: deu-lit
metrics:
- name: BLEU
type: bleu
value: 22.6
- name: chr-F
type: chrf
value: 0.54957
- task:
name: Translation eng-lit
type: translation
args: eng-lit
dataset:
name: flores200-devtest
type: flores200-devtest
args: eng-lit
metrics:
- name: BLEU
type: bleu
value: 27.7
- name: chr-F
type: chrf
value: 0.59338
- task:
name: Translation fra-lit
type: translation
args: fra-lit
dataset:
name: flores200-devtest
type: flores200-devtest
args: fra-lit
metrics:
- name: BLEU
type: bleu
value: 22.3
- name: chr-F
type: chrf
value: 0.54683
- task:
name: Translation por-lit
type: translation
args: por-lit
dataset:
name: flores200-devtest
type: flores200-devtest
args: por-lit
metrics:
- name: BLEU
type: bleu
value: 22.6
- name: chr-F
type: chrf
value: 0.55033
- task:
name: Translation spa-lit
type: translation
args: spa-lit
dataset:
name: flores200-devtest
type: flores200-devtest
args: spa-lit
metrics:
- name: BLEU
type: bleu
value: 16.9
- name: chr-F
type: chrf
value: 0.50725
- task:
name: Translation deu-lav
type: translation
args: deu-lav
dataset:
name: flores101-devtest
type: flores_101
args: deu lav devtest
metrics:
- name: BLEU
type: bleu
value: 24.4
- name: chr-F
type: chrf
value: 0.54724
- task:
name: Translation eng-lav
type: translation
args: eng-lav
dataset:
name: flores101-devtest
type: flores_101
args: eng lav devtest
metrics:
- name: BLEU
type: bleu
value: 31
- name: chr-F
type: chrf
value: 0.59955
- task:
name: Translation eng-lit
type: translation
args: eng-lit
dataset:
name: flores101-devtest
type: flores_101
args: eng lit devtest
metrics:
- name: BLEU
type: bleu
value: 27.2
- name: chr-F
type: chrf
value: 0.58961
- task:
name: Translation fra-lav
type: translation
args: fra-lav
dataset:
name: flores101-devtest
type: flores_101
args: fra lav devtest
metrics:
- name: BLEU
type: bleu
value: 24.2
- name: chr-F
type: chrf
value: 0.54276
- task:
name: Translation fra-lit
type: translation
args: fra-lit
dataset:
name: flores101-devtest
type: flores_101
args: fra lit devtest
metrics:
- name: BLEU
type: bleu
value: 22.4
- name: chr-F
type: chrf
value: 0.54665
- task:
name: Translation spa-lav
type: translation
args: spa-lav
dataset:
name: flores101-devtest
type: flores_101
args: spa lav devtest
metrics:
- name: BLEU
type: bleu
value: 17.8
- name: chr-F
type: chrf
value: 0.50131
- task:
name: Translation deu-lav
type: translation
args: deu-lav
dataset:
name: ntrex128
type: ntrex128
args: deu-lav
metrics:
- name: BLEU
type: bleu
value: 16.8
- name: chr-F
type: chrf
value: 0.4798
- task:
name: Translation deu-lit
type: translation
args: deu-lit
dataset:
name: ntrex128
type: ntrex128
args: deu-lit
metrics:
- name: BLEU
type: bleu
value: 17.6
- name: chr-F
type: chrf
value: 0.50645
- task:
name: Translation eng-lav
type: translation
args: eng-lav
dataset:
name: ntrex128
type: ntrex128
args: eng-lav
metrics:
- name: BLEU
type: bleu
value: 20.6
- name: chr-F
type: chrf
value: 0.51026
- task:
name: Translation eng-lit
type: translation
args: eng-lit
dataset:
name: ntrex128
type: ntrex128
args: eng-lit
metrics:
- name: BLEU
type: bleu
value: 21.5
- name: chr-F
type: chrf
value: 0.54187
- task:
name: Translation fra-lav
type: translation
args: fra-lav
dataset:
name: ntrex128
type: ntrex128
args: fra-lav
metrics:
- name: BLEU
type: bleu
value: 15.5
- name: chr-F
type: chrf
value: 0.45346
- task:
name: Translation fra-lit
type: translation
args: fra-lit
dataset:
name: ntrex128
type: ntrex128
args: fra-lit
metrics:
- name: BLEU
type: bleu
value: 16.2
- name: chr-F
type: chrf
value: 0.4887
- task:
name: Translation por-lav
type: translation
args: por-lav
dataset:
name: ntrex128
type: ntrex128
args: por-lav
metrics:
- name: BLEU
type: bleu
value: 17.3
- name: chr-F
type: chrf
value: 0.47809
- task:
name: Translation por-lit
type: translation
args: por-lit
dataset:
name: ntrex128
type: ntrex128
args: por-lit
metrics:
- name: BLEU
type: bleu
value: 17.5
- name: chr-F
type: chrf
value: 0.50653
- task:
name: Translation spa-lav
type: translation
args: spa-lav
dataset:
name: ntrex128
type: ntrex128
args: spa-lav
metrics:
- name: BLEU
type: bleu
value: 17.1
- name: chr-F
type: chrf
value: 0.4769
- task:
name: Translation spa-lit
type: translation
args: spa-lit
dataset:
name: ntrex128
type: ntrex128
args: spa-lit
metrics:
- name: BLEU
type: bleu
value: 17.1
- name: chr-F
type: chrf
value: 0.50412
- task:
name: Translation deu-lit
type: translation
args: deu-lit
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: deu-lit
metrics:
- name: BLEU
type: bleu
value: 39.8
- name: chr-F
type: chrf
value: 0.65379
- task:
name: Translation eng-lav
type: translation
args: eng-lav
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: eng-lav
metrics:
- name: BLEU
type: bleu
value: 46.4
- name: chr-F
type: chrf
value: 0.68823
- task:
name: Translation eng-lit
type: translation
args: eng-lit
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: eng-lit
metrics:
- name: BLEU
type: bleu
value: 39.8
- name: chr-F
type: chrf
value: 0.67792
- 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: 43.3
- name: chr-F
type: chrf
value: 0.68018
- task:
name: Translation spa-lit
type: translation
args: spa-lit
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: spa-lit
metrics:
- name: BLEU
type: bleu
value: 43.3
- name: chr-F
type: chrf
value: 0.68133
- task:
name: Translation eng-lav
type: translation
args: eng-lav
dataset:
name: newstest2017
type: wmt-2017-news
args: eng-lav
metrics:
- name: BLEU
type: bleu
value: 21.5
- name: chr-F
type: chrf
value: 0.53192
- task:
name: Translation eng-lit
type: translation
args: eng-lit
dataset:
name: newstest2019
type: wmt-2019-news
args: eng-lit
metrics:
- name: BLEU
type: bleu
value: 18.3
- name: chr-F
type: chrf
value: 0.51714
opus-mt-tc-bible-big-deu_eng_fra_por_spa-bat
Table of Contents
- Model Details
- Uses
- Risks, Limitations and Biases
- How to Get Started With the Model
- Training
- Evaluation
- Citation Information
- Acknowledgements
Model Details
Neural machine translation model for translating from unknown (deu+eng+fra+por+spa) to Baltic languages (bat).
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:
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:
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.)
@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