|
|
--- |
|
|
language: |
|
|
- multilingual |
|
|
- af |
|
|
- als |
|
|
- am |
|
|
- an |
|
|
- ar |
|
|
- arz |
|
|
- as |
|
|
- ast |
|
|
- av |
|
|
- az |
|
|
- azb |
|
|
- ba |
|
|
- bar |
|
|
- bcl |
|
|
- be |
|
|
- bg |
|
|
- bh |
|
|
- bn |
|
|
- bo |
|
|
- bpy |
|
|
- br |
|
|
- bs |
|
|
- bxr |
|
|
- ca |
|
|
- cbk |
|
|
- ce |
|
|
- ceb |
|
|
- ckb |
|
|
- co |
|
|
- cs |
|
|
- cv |
|
|
- cy |
|
|
- da |
|
|
- de |
|
|
- diq |
|
|
- dsb |
|
|
- dty |
|
|
- dv |
|
|
- el |
|
|
- eml |
|
|
- en |
|
|
- eo |
|
|
- es |
|
|
- et |
|
|
- eu |
|
|
- fa |
|
|
- fi |
|
|
- fr |
|
|
- frr |
|
|
- fy |
|
|
- ga |
|
|
- gd |
|
|
- gl |
|
|
- gn |
|
|
- gom |
|
|
- gu |
|
|
- gv |
|
|
- he |
|
|
- hi |
|
|
- hif |
|
|
- hr |
|
|
- hsb |
|
|
- ht |
|
|
- hu |
|
|
- hy |
|
|
- ia |
|
|
- id |
|
|
- ie |
|
|
- ilo |
|
|
- io |
|
|
- is |
|
|
- it |
|
|
- ja |
|
|
- jbo |
|
|
- jv |
|
|
- ka |
|
|
- kk |
|
|
- km |
|
|
- kn |
|
|
- ko |
|
|
- krc |
|
|
- ku |
|
|
- kv |
|
|
- kw |
|
|
- ky |
|
|
- la |
|
|
- lb |
|
|
- lez |
|
|
- li |
|
|
- lmo |
|
|
- lo |
|
|
- lrc |
|
|
- lt |
|
|
- lv |
|
|
- mai |
|
|
- mg |
|
|
- mhr |
|
|
- min |
|
|
- mk |
|
|
- ml |
|
|
- mn |
|
|
- mr |
|
|
- mrj |
|
|
- ms |
|
|
- mt |
|
|
- mwl |
|
|
- my |
|
|
- myv |
|
|
- mzn |
|
|
- nah |
|
|
- nap |
|
|
- nds |
|
|
- ne |
|
|
- new |
|
|
- nl |
|
|
- nn |
|
|
- no |
|
|
- oc |
|
|
- or |
|
|
- os |
|
|
- pa |
|
|
- pam |
|
|
- pfl |
|
|
- pl |
|
|
- pms |
|
|
- pnb |
|
|
- ps |
|
|
- pt |
|
|
- qu |
|
|
- rm |
|
|
- ro |
|
|
- ru |
|
|
- rue |
|
|
- sa |
|
|
- sah |
|
|
- sc |
|
|
- scn |
|
|
- sco |
|
|
- sd |
|
|
- sh |
|
|
- si |
|
|
- sk |
|
|
- sl |
|
|
- so |
|
|
- sq |
|
|
- sr |
|
|
- su |
|
|
- sv |
|
|
- sw |
|
|
- ta |
|
|
- te |
|
|
- tg |
|
|
- th |
|
|
- tk |
|
|
- tl |
|
|
- tr |
|
|
- tt |
|
|
- tyv |
|
|
- ug |
|
|
- uk |
|
|
- ur |
|
|
- uz |
|
|
- vec |
|
|
- vep |
|
|
- vi |
|
|
- vls |
|
|
- vo |
|
|
- wa |
|
|
- war |
|
|
- wuu |
|
|
- xal |
|
|
- xmf |
|
|
- yi |
|
|
- yo |
|
|
- yue |
|
|
- zh |
|
|
tags: |
|
|
- fasttext |
|
|
datasets: |
|
|
- wikipedia |
|
|
- tatoeba |
|
|
- setimes |
|
|
license: cc-by-sa-4.0 |
|
|
library_name: fasttext |
|
|
inference: false |
|
|
--- |
|
|
|
|
|
## FastText model for language identification |
|
|
|
|
|
#### ♻️ Imported from https://fasttext.cc/docs/en/language-identification.html |
|
|
|
|
|
> [1] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, Bag of Tricks for Efficient Text Classification |
|
|
|
|
|
```bibtex |
|
|
@article{joulin2016bag, |
|
|
title={Bag of Tricks for Efficient Text Classification}, |
|
|
author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas}, |
|
|
journal={arXiv preprint arXiv:1607.01759}, |
|
|
year={2016} |
|
|
} |
|
|
``` |
|
|
|
|
|
> [2] A. Joulin, E. Grave, P. Bojanowski, M. Douze, H. Jégou, T. Mikolov, FastText.zip: Compressing text classification models |
|
|
|
|
|
```bibtex |
|
|
@article{joulin2016fasttext, |
|
|
title={FastText.zip: Compressing text classification models}, |
|
|
author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Douze, Matthijs and J{\'e}gou, H{\'e}rve and Mikolov, Tomas}, |
|
|
journal={arXiv preprint arXiv:1612.03651}, |
|
|
year={2016} |
|
|
} |
|
|
``` |
