Code for languages, based on ISO 639-1
secou opened this issue · comments
Serge Courrier commented
Hi (and thanks for the list). Could be interesting to precise that the lang: syntax is based on ISO 639-1 codes.
https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes
Sometimes... the detection is poor (for example co, eu, br...)
Igor Brigadir commented
Yep - i might add a note and link to https://blog.twitter.com/engineering/en_us/a/2015/evaluating-language-identification-performance.html - that discusses accuracy a bit too.
Igor Brigadir commented
Added, thanks!