🚀 Bantu Languages to English Translation Model
This project focuses on a translation model that translates from Bantu languages to English. It provides details about the model, its performance, and relevant system information.
✨ Features
- Multilingual Support: Supports multiple Bantu languages including
sn, zu, rw, lg, ts, ln, ny, xh, rn, bnt for translation to English.
- Transformer Model: Utilizes a transformer model for translation tasks.
- Pre - processing: Applies normalization and SentencePiece (spm32k, spm32k) for pre - processing.
📦 Installation
No specific installation steps are provided in the original document.
📚 Documentation
Bantu to English Translation Details
-
Source Group: Bantu languages
-
Target Group: English
-
OPUS Readme: [bnt - eng](https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/bnt - eng/README.md)
-
Model: transformer
-
Source Languages: kin, lin, lug, nya, run, sna, swh, toi_Latn, tso, umb, xho, zul
-
Target Language: eng
-
Pre - processing: normalization + SentencePiece (spm32k, spm32k)
-
Download Original Weights: [opus2m - 2020 - 07 - 31.zip](https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.zip)
-
Test Set Translations: [opus2m - 2020 - 07 - 31.test.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.test.txt)
-
Test Set Scores: [opus2m - 2020 - 07 - 31.eval.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.eval.txt)
Benchmarks
| Testset |
BLEU |
chr - F |
| Tatoeba - test.kin - eng.kin.eng |
31.7 |
0.481 |
| Tatoeba - test.lin - eng.lin.eng |
8.3 |
0.271 |
| Tatoeba - test.lug - eng.lug.eng |
5.3 |
0.128 |
| Tatoeba - test.multi.eng |
23.1 |
0.394 |
| Tatoeba - test.nya - eng.nya.eng |
38.3 |
0.527 |
| Tatoeba - test.run - eng.run.eng |
26.6 |
0.431 |
| Tatoeba - test.sna - eng.sna.eng |
27.5 |
0.440 |
| Tatoeba - test.swa - eng.swa.eng |
4.6 |
0.195 |
| Tatoeba - test.toi - eng.toi.eng |
16.2 |
0.342 |
| Tatoeba - test.tso - eng.tso.eng |
100.0 |
1.000 |
| Tatoeba - test.umb - eng.umb.eng |
8.4 |
0.231 |
| Tatoeba - test.xho - eng.xho.eng |
37.2 |
0.554 |
| Tatoeba - test.zul - eng.zul.eng |
40.9 |
0.576 |
System Info
| Property |
Details |
| hf_name |
bnt - eng |
| Source Languages |
bnt |
| Target Languages |
eng |
| Opus Readme URL |
[https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/bnt - eng/README.md](https://github.com/Helsinki - NLP/Tatoeba - Challenge/tree/master/models/bnt - eng/README.md) |
| Original Repo |
Tatoeba - Challenge |
| Tags |
['translation'] |
| Languages |
['sn', 'zu', 'rw', 'lg', 'ts', 'ln', 'ny', 'xh', 'rn', 'bnt', 'en'] |
| Source Constituents |
{'sna', 'zul', 'kin', 'lug', 'tso', 'lin', 'nya', 'xho', 'swh', 'run', 'toi_Latn', 'umb'} |
| Target Constituents |
{'eng'} |
| Source Multilingual |
True |
| Target Multilingual |
False |
| Pre - processing |
normalization + SentencePiece (spm32k, spm32k) |
| URL Model |
[https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.zip](https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.zip) |
| URL Test Set |
[https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.test.txt](https://object.pouta.csc.fi/Tatoeba - MT - models/bnt - eng/opus2m - 2020 - 07 - 31.test.txt) |
| Source Alpha3 |
bnt |
| Target Alpha3 |
eng |
| Short Pair |
bnt - en |
| chrF2 Score |
0.39399999999999996 |
| BLEU |
23.1 |
| Brevity Penalty |
1.0 |
| Ref Len |
14565.0 |
| Source Name |
Bantu languages |
| Target Name |
English |
| Train Date |
2020 - 07 - 31 |
| Source Alpha2 |
bnt |
| Target Alpha2 |
en |
| Prefer Old |
False |
| Long Pair |
bnt - eng |
| Helsinki Git SHA |
480fcbe0ee1bf4774bcbe6226ad9f58e63f6c535 |
| Transformers Git SHA |
2207e5d8cb224e954a7cba69fa4ac2309e9ff30b |
| Port Machine |
brutasse |
| Port Time |
2020 - 08 - 21 - 14:41 |
📄 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)
