đ eng-fiu Translation Model
This project focuses on the translation from English to Finno - Ugrian languages. It provides a transformer - based model with specific pre - processing steps and offers detailed evaluation scores on various test sets.
đ Quick Start
To start using this model, you need to download the original weights and test set translations from the provided links:
⨠Features
- Language Support: Supports translation from English to multiple Finno - Ugrian languages including Estonian, Finnish, Hungarian, etc.
- Pre - processing: Utilizes normalization and SentencePiece (spm32k, spm32k) for pre - processing.
- Benchmark Scores: Provides BLEU and chr - F scores on a variety of test sets.
đĻ Installation
No specific installation steps are provided in the original document.
đ Documentation
Model Details
| Property |
Details |
| Model Type |
Transformer |
| Source Language(s) |
eng |
| Target Language(s) |
est, fin, fkv_Latn, hun, izh, kpv, krl, liv_Latn, mdf, mhr, myv, sma, sme, udm, vro |
| Pre - processing |
normalization + SentencePiece (spm32k, spm32k) |
| Initial Language Token |
A sentence initial language token is required in the form of >>id<< (id = valid target language ID) |
Benchmarks
| testset |
BLEU |
chr - F |
| newsdev2015 - enfi - engfin.eng.fin |
18.7 |
0.522 |
| newsdev2018 - enet - engest.eng.est |
19.4 |
0.521 |
| newssyscomb2009 - enghun.eng.hun |
15.5 |
0.472 |
| newstest2009 - enghun.eng.hun |
15.4 |
0.468 |
| newstest2015 - enfi - engfin.eng.fin |
19.9 |
0.532 |
| newstest2016 - enfi - engfin.eng.fin |
21.1 |
0.544 |
| newstest2017 - enfi - engfin.eng.fin |
23.8 |
0.567 |
| newstest2018 - enet - engest.eng.est |
20.4 |
0.532 |
| newstest2018 - enfi - engfin.eng.fin |
15.6 |
0.498 |
| newstest2019 - enfi - engfin.eng.fin |
20.0 |
0.520 |
| newstestB2016 - enfi - engfin.eng.fin |
17.0 |
0.512 |
| newstestB2017 - enfi - engfin.eng.fin |
19.7 |
0.531 |
| Tatoeba - test.eng - chm.eng.chm |
0.9 |
0.115 |
| Tatoeba - test.eng - est.eng.est |
49.8 |
0.689 |
| Tatoeba - test.eng - fin.eng.fin |
34.7 |
0.597 |
| Tatoeba - test.eng - fkv.eng.fkv |
1.3 |
0.187 |
| Tatoeba - test.eng - hun.eng.hun |
35.2 |
0.589 |
| Tatoeba - test.eng - izh.eng.izh |
6.0 |
0.163 |
| Tatoeba - test.eng - kom.eng.kom |
3.4 |
0.012 |
| Tatoeba - test.eng - krl.eng.krl |
6.4 |
0.202 |
| Tatoeba - test.eng - liv.eng.liv |
1.6 |
0.102 |
| Tatoeba - test.eng - mdf.eng.mdf |
3.7 |
0.008 |
| Tatoeba - test.eng.multi |
35.4 |
0.590 |
| Tatoeba - test.eng - myv.eng.myv |
1.4 |
0.014 |
| Tatoeba - test.eng - sma.eng.sma |
2.6 |
0.097 |
| Tatoeba - test.eng - sme.eng.sme |
7.3 |
0.221 |
| Tatoeba - test.eng - udm.eng.udm |
1.4 |
0.079 |
System Info
- hf_name: eng - fiu
- source_languages: eng
- target_languages: fiu
- opus_readme_url: https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/eng - fiu/README.md
- original_repo: Tatoeba - Challenge
- tags: ['translation']
- languages: ['en', 'se', 'fi', 'hu', 'et', 'fiu']
- src_constituents: {'eng'}
- tgt_constituents: {'izh', 'mdf', 'vep', 'vro', 'sme', 'myv', 'fkv_Latn', 'krl', 'fin', 'hun', 'kpv', 'udm', 'liv_Latn', 'est', 'mhr', 'sma'}
- src_multilingual: False
- tgt_multilingual: True
- prepro: normalization + SentencePiece (spm32k, spm32k)
- url_model: https://object.pouta.csc.fi/Tatoeba - MT - models/eng - fiu/opus2m - 2020 - 08 - 01.zip
- url_test_set: https://object.pouta.csc.fi/Tatoeba - MT - models/eng - fiu/opus2m - 2020 - 08 - 01.test.txt
- src_alpha3: eng
- tgt_alpha3: fiu
- short_pair: en - fiu
- chrF2_score: 0.59
- bleu: 35.4
- brevity_penalty: 0.9440000000000001
- ref_len: 59311.0
- src_name: English
- tgt_name: Finno - Ugrian languages
- train_date: 2020 - 08 - 01
- src_alpha2: en
- tgt_alpha2: fiu
- prefer_old: False
- long_pair: eng - fiu
- 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.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
