https://bugs.documentfoundation.org/show_bug.cgi?id=91766

--- Comment #21 from Shantanu <[email protected]> ---
As Mike Kaganski has already noted, the current implementation is not
functioning as intended. The library "libexttextcat" is an N-gram-based text
categorization tool. I recommend integrating a machine learning–based language
identification model such as FastText. The model lid.176.ftz is lightweight
(under 1 MB), highly accurate, and efficient.

https://fasttext.cc/docs/en/language-identification.html

-- 
You are receiving this mail because:
You are the assignee for the bug.

Reply via email to