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-bat-deu_eng_fra_por_spa
results:
- task:
name: Translation lit-deu
type: translation
args: lit-deu
dataset:
name: flores200-devtest
type: flores200-devtest
args: lit-deu
metrics:
- name: BLEU
type: bleu
value: 23.7
- name: chr-F
type: chrf
value: 0.53223
- task:
name: Translation lit-eng
type: translation
args: lit-eng
dataset:
name: flores200-devtest
type: flores200-devtest
args: lit-eng
metrics:
- name: BLEU
type: bleu
value: 32.6
- name: chr-F
type: chrf
value: 0.59361
- task:
name: Translation lit-fra
type: translation
args: lit-fra
dataset:
name: flores200-devtest
type: flores200-devtest
args: lit-fra
metrics:
- name: BLEU
type: bleu
value: 30
- name: chr-F
type: chrf
value: 0.56786
- task:
name: Translation lit-por
type: translation
args: lit-por
dataset:
name: flores200-devtest
type: flores200-devtest
args: lit-por
metrics:
- name: BLEU
type: bleu
value: 28.2
- name: chr-F
type: chrf
value: 0.55393
- task:
name: Translation lit-spa
type: translation
args: lit-spa
dataset:
name: flores200-devtest
type: flores200-devtest
args: lit-spa
metrics:
- name: BLEU
type: bleu
value: 20.9
- name: chr-F
type: chrf
value: 0.49041
- task:
name: Translation lav-deu
type: translation
args: lav-deu
dataset:
name: flores101-devtest
type: flores_101
args: lav deu devtest
metrics:
- name: BLEU
type: bleu
value: 23.8
- name: chr-F
type: chrf
value: 0.54001
- task:
name: Translation lav-fra
type: translation
args: lav-fra
dataset:
name: flores101-devtest
type: flores_101
args: lav fra devtest
metrics:
- name: BLEU
type: bleu
value: 29.4
- name: chr-F
type: chrf
value: 0.57002
- task:
name: Translation lav-por
type: translation
args: lav-por
dataset:
name: flores101-devtest
type: flores_101
args: lav por devtest
metrics:
- name: BLEU
type: bleu
value: 26.7
- name: chr-F
type: chrf
value: 0.55155
- task:
name: Translation lav-spa
type: translation
args: lav-spa
dataset:
name: flores101-devtest
type: flores_101
args: lav spa devtest
metrics:
- name: BLEU
type: bleu
value: 20.8
- name: chr-F
type: chrf
value: 0.49259
- task:
name: Translation lit-eng
type: translation
args: lit-eng
dataset:
name: flores101-devtest
type: flores_101
args: lit eng devtest
metrics:
- name: BLEU
type: bleu
value: 32.1
- name: chr-F
type: chrf
value: 0.59073
- task:
name: Translation lit-por
type: translation
args: lit-por
dataset:
name: flores101-devtest
type: flores_101
args: lit por devtest
metrics:
- name: BLEU
type: bleu
value: 27.8
- name: chr-F
type: chrf
value: 0.55106
- task:
name: Translation lav-deu
type: translation
args: lav-deu
dataset:
name: ntrex128
type: ntrex128
args: lav-deu
metrics:
- name: BLEU
type: bleu
value: 18.5
- name: chr-F
type: chrf
value: 0.47317
- task:
name: Translation lav-eng
type: translation
args: lav-eng
dataset:
name: ntrex128
type: ntrex128
args: lav-eng
metrics:
- name: BLEU
type: bleu
value: 19.7
- name: chr-F
type: chrf
value: 0.53734
- task:
name: Translation lav-fra
type: translation
args: lav-fra
dataset:
name: ntrex128
type: ntrex128
args: lav-fra
metrics:
- name: BLEU
type: bleu
value: 19.6
- name: chr-F
type: chrf
value: 0.47843
- task:
name: Translation lav-por
type: translation
args: lav-por
dataset:
name: ntrex128
type: ntrex128
args: lav-por
metrics:
- name: BLEU
type: bleu
value: 19.3
- name: chr-F
type: chrf
value: 0.47027
- task:
name: Translation lav-spa
type: translation
args: lav-spa
dataset:
name: ntrex128
type: ntrex128
args: lav-spa
metrics:
- name: BLEU
type: bleu
value: 22.7
- name: chr-F
type: chrf
value: 0.49428
- task:
name: Translation lit-deu
type: translation
args: lit-deu
dataset:
name: ntrex128
type: ntrex128
args: lit-deu
metrics:
- name: BLEU
type: bleu
value: 19.4
- name: chr-F
type: chrf
value: 0.50279
- task:
name: Translation lit-eng
type: translation
args: lit-eng
dataset:
name: ntrex128
type: ntrex128
args: lit-eng
metrics:
- name: BLEU
type: bleu
value: 28.1
- name: chr-F
type: chrf
value: 0.56642
- task:
name: Translation lit-fra
type: translation
args: lit-fra
dataset:
name: ntrex128
type: ntrex128
args: lit-fra
metrics:
- name: BLEU
type: bleu
value: 22.6
- name: chr-F
type: chrf
value: 0.51276
- task:
name: Translation lit-por
type: translation
args: lit-por
dataset:
name: ntrex128
type: ntrex128
args: lit-por
metrics:
- name: BLEU
type: bleu
value: 22.6
- name: chr-F
type: chrf
value: 0.50864
- task:
name: Translation lit-spa
type: translation
args: lit-spa
dataset:
name: ntrex128
type: ntrex128
args: lit-spa
metrics:
- name: BLEU
type: bleu
value: 25.9
- name: chr-F
type: chrf
value: 0.53105
- task:
name: Translation lav-eng
type: translation
args: lav-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: lav-eng
metrics:
- name: BLEU
type: bleu
value: 21.5
- name: chr-F
type: chrf
value: 0.63015
- task:
name: Translation lit-deu
type: translation
args: lit-deu
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: lit-deu
metrics:
- name: BLEU
type: bleu
value: 47.5
- name: chr-F
type: chrf
value: 0.66527
- task:
name: Translation lit-eng
type: translation
args: lit-eng
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: lit-eng
metrics:
- name: BLEU
type: bleu
value: 58.9
- name: chr-F
type: chrf
value: 0.72975
- task:
name: Translation lit-spa
type: translation
args: lit-spa
dataset:
name: tatoeba-test-v2021-08-07
type: tatoeba_mt
args: lit-spa
metrics:
- name: BLEU
type: bleu
value: 49.9
- name: chr-F
type: chrf
value: 0.67956
- 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: 55.5
- name: chr-F
type: chrf
value: 0.71003
- task:
name: Translation lav-eng
type: translation
args: lav-eng
dataset:
name: newstest2017
type: wmt-2017-news
args: lav-eng
metrics:
- name: BLEU
type: bleu
value: 22
- name: chr-F
type: chrf
value: 0.49729
- task:
name: Translation lit-eng
type: translation
args: lit-eng
dataset:
name: newstest2019
type: wmt-2019-news
args: lit-eng
metrics:
- name: BLEU
type: bleu
value: 31.2
- name: chr-F
type: chrf
value: 0.59971
opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa
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 Baltic languages (bat) to unknown (deu+eng+fra+por+spa).
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): lav lit prg sgs
- Target Language(s): deu eng fra por spa
- Valid Target Language Labels: >>deu<< >>eng<< >>fra<< >>por<< >>spa<< >>xxx<<
- 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. >>deu<<
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 = [
">>deu<< Replace this with text in an accepted source language.",
">>spa<< This is the second sentence."
]
model_name = "pytorch-models/opus-mt-tc-bible-big-bat-deu_eng_fra_por_spa"
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-bat-deu_eng_fra_por_spa")
print(pipe(">>deu<< 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 |
|---|---|---|---|---|---|
| lav-eng | tatoeba-test-v2021-08-07 | 0.63015 | 21.5 | 1631 | 11213 |
| lit-deu | tatoeba-test-v2021-08-07 | 0.66527 | 47.5 | 1115 | 8531 |
| lit-eng | tatoeba-test-v2021-08-07 | 0.72975 | 58.9 | 2528 | 17855 |
| lit-spa | tatoeba-test-v2021-08-07 | 0.67956 | 49.9 | 454 | 2751 |
| lav-deu | flores101-devtest | 0.54001 | 23.8 | 1012 | 25094 |
| lav-fra | flores101-devtest | 0.57002 | 29.4 | 1012 | 28343 |
| lav-por | flores101-devtest | 0.55155 | 26.7 | 1012 | 26519 |
| lav-spa | flores101-devtest | 0.49259 | 20.8 | 1012 | 29199 |
| lit-eng | flores101-devtest | 0.59073 | 32.1 | 1012 | 24721 |
| lit-por | flores101-devtest | 0.55106 | 27.8 | 1012 | 26519 |
| lit-deu | flores200-devtest | 0.53223 | 23.7 | 1012 | 25094 |
| lit-eng | flores200-devtest | 0.59361 | 32.6 | 1012 | 24721 |
| lit-fra | flores200-devtest | 0.56786 | 30.0 | 1012 | 28343 |
| lit-por | flores200-devtest | 0.55393 | 28.2 | 1012 | 26519 |
| lit-spa | flores200-devtest | 0.49041 | 20.9 | 1012 | 29199 |
| lav-eng | newstest2017 | 0.49729 | 22.0 | 2001 | 47511 |
| lit-eng | newstest2019 | 0.59971 | 31.2 | 1000 | 25878 |
| lav-deu | ntrex128 | 0.47317 | 18.5 | 1997 | 48761 |
| lav-eng | ntrex128 | 0.53734 | 19.7 | 1997 | 47673 |
| lav-fra | ntrex128 | 0.47843 | 19.6 | 1997 | 53481 |
| lav-por | ntrex128 | 0.47027 | 19.3 | 1997 | 51631 |
| lav-spa | ntrex128 | 0.49428 | 22.7 | 1997 | 54107 |
| lit-deu | ntrex128 | 0.50279 | 19.4 | 1997 | 48761 |
| lit-eng | ntrex128 | 0.56642 | 28.1 | 1997 | 47673 |
| lit-fra | ntrex128 | 0.51276 | 22.6 | 1997 | 53481 |
| lit-por | ntrex128 | 0.50864 | 22.6 | 1997 | 51631 |
| lit-spa | ntrex128 | 0.53105 | 25.9 | 1997 | 54107 |
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: a0ea3b3
- port time: Mon Oct 7 17:27:51 EEST 2024
- port machine: LM0-400-22516.local