eellak / nlpbuddy

A text analysis application for performing common NLP tasks through a web dashboard interface and an API
http://www.nlpbuddy.io/
GNU Affero General Public License v3.0
123 stars 28 forks source link

language identification #7

Open mgogoulos opened 6 years ago

mgogoulos commented 6 years ago

just tried with https://github.com/saffsd/langid.py

also check fastText: https://fasttext.cc/blog/2017/10/02/blog-post.html

giannisdaras commented 5 years ago

It would be really cool to have this :)

mgogoulos commented 5 years ago

language identification is now performed via the first library (langid), fastText reports that it achieves better performance, it would be nice to try it as well. Shouldn't be hard to integrate