đ afr-rus Translation Model
This project focuses on Afrikaans to Russian translation, offering a transformer - align model with specific pre - processing and evaluation metrics.
đ Quick Start
The afr - rus model is designed for translating Afrikaans text to Russian. You can access the model's original weights, test set translations, and evaluation scores through the provided links.
⨠Features
- Language Pair: Translates from Afrikaans (
afr
) to Russian (rus
).
- Model Type: Uses the
transformer - align
model.
- Pre - processing: Applies normalization and SentencePiece (spm32k, spm32k).
đĻ Installation
No specific installation steps are provided in the original document.
đģ Usage Examples
No code examples are provided in the original document.
đ Documentation
Model Details
- Source Group: Afrikaans
- Target Group: Russian
- OPUS Readme: [afr - rus](https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/afr - rus/README.md)
- Model:
transformer - align
- Pre - processing: normalization + SentencePiece (spm32k, spm32k)
- Download Original Weights: [opus - 2020 - 06 - 17.zip](https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.zip)
- Test Set Translations: [opus - 2020 - 06 - 17.test.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.test.txt)
- Test Set Scores: [opus - 2020 - 06 - 17.eval.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.eval.txt)
Benchmarks
Testset |
BLEU |
chr - F |
Tatoeba - test.afr.rus |
38.2 |
0.580 |
System Info
Property |
Details |
hf_name |
afr - rus |
source_languages |
afr |
target_languages |
rus |
opus_readme_url |
[https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/afr - rus/README.md](https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/afr - rus/README.md) |
original_repo |
Tatoeba - Challenge |
tags |
['translation'] |
languages |
['af', 'ru'] |
src_constituents |
{'afr'} |
tgt_constituents |
{'rus'} |
src_multilingual |
False |
tgt_multilingual |
False |
prepro |
normalization + SentencePiece (spm32k, spm32k) |
url_model |
[https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.zip](https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.zip) |
url_test_set |
[https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.test.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/afr - rus/opus - 2020 - 06 - 17.test.txt) |
src_alpha3 |
afr |
tgt_alpha3 |
rus |
short_pair |
af - ru |
chrF2_score |
0.58 |
bleu |
38.2 |
brevity_penalty |
0.992 |
ref_len |
1213.0 |
src_name |
Afrikaans |
tgt_name |
Russian |
train_date |
2020 - 06 - 17 |
src_alpha2 |
af |
tgt_alpha2 |
ru |
prefer_old |
False |
long_pair |
afr - rus |
helsinki_git_sha |
480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535 |
transformers_git_sha |
2207e5d8cb224e954a7cba69fa4ac2309e9ff30b |
port_machine |
brutasse |
port_time |
2020 - 08 - 21 - 14:41 |
đ License
This project is licensed under the apache - 2.0
license.