Geek Answers Handbook

Language Discovery API / Library

Is there a service / library (free or paid) that takes a piece of text and returns its language?

I need to go through a million blog posts and identify their languages.

+5
source share
2 answers

I think this is the best!

https://code.google.com/p/language-detection/

+5
source

I heard good things about langid.py .

README Features:

  • Fast
  • Pre-prepared in a large number of languages ​​(currently 97)
  • Insensitive to domain specific functions (e.g. HTML / XML markup)
  • Separate .py file with minimal dependencies
  • Deployment as a web service

https://github.com/saffsd/langid.py

0
source

More articles:


All Articles