đ Hun - Ukr Translation Model
This project focuses on the translation between Hungarian and Ukrainian. It provides a specific model and related data for this language - pair translation task, offering valuable resources for the field of natural language processing.
đ Quick Start
The main information about this Hungarian - Ukrainian translation model is as follows:
- Source Group: Hungarian
- Target Group: Ukrainian
- OPUS Readme: [hun - ukr](https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/hun - ukr/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/hun - ukr/opus - 2020 - 06 - 17.zip)
- Test Set Translations: [opus - 2020 - 06 - 17.test.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/hun - ukr/opus - 2020 - 06 - 17.test.txt)
- Test Set Scores: [opus - 2020 - 06 - 17.eval.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/hun - ukr/opus - 2020 - 06 - 17.eval.txt)
đ Documentation
Model Details
Property |
Details |
Source Languages |
hun |
Target Languages |
ukr |
Model Type |
transformer - align |
Pre - processing |
normalization + SentencePiece (spm32k,spm32k) |
Benchmarks
Testset |
BLEU |
chr - F |
Tatoeba - test.hun.ukr |
41.2 |
0.611 |
System Info
Property |
Details |
hf_name |
hun - ukr |
source_languages |
hun |
target_languages |
ukr |
opus_readme_url |
[https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/hun - ukr/README.md](https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/hun - ukr/README.md) |
original_repo |
Tatoeba - Challenge |
tags |
['translation'] |
languages |
['hu', 'uk'] |
src_constituents |
{'hun'} |
tgt_constituents |
{'ukr'} |
src_multilingual |
False |
tgt_multilingual |
False |
prepro |
normalization + SentencePiece (spm32k,spm32k) |
url_model |
[https://object.pouta.csc.fi/Tatoeba - MT - models/hun - ukr/opus - 2020 - 06 - 17.zip](https://object.pouta.csc.fi/Tatoeba - MT - models/hun - ukr/opus - 2020 - 06 - 17.zip) |
url_test_set |
[https://object.pouta.csc.fi/Tatoeba - MT - models/hun - ukr/opus - 2020 - 06 - 17.test.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/hun - ukr/opus - 2020 - 06 - 17.test.txt) |
src_alpha3 |
hun |
tgt_alpha3 |
ukr |
short_pair |
hu - uk |
chrF2_score |
0.611 |
bleu |
41.2 |
brevity_penalty |
0.966 |
ref_len |
2568.0 |
src_name |
Hungarian |
tgt_name |
Ukrainian |
train_date |
2020 - 06 - 17 |
src_alpha2 |
hu |
tgt_alpha2 |
uk |
prefer_old |
False |
long_pair |
hun - ukr |
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.