Evaluate other language identification methods.

[greyblake]

This is issue is a reminder for myself.

Possible options:

• Chars frequencies
• 2-grams?
• The most frequent words (100 or 1000)?
• Smart/complex resolve between LangA and LangB by identifying traits that are present in one language and absent in another. - This could help when 2 languages have a very similar statistical characteristics.
• Řehůřek and Kolkus (2009)

See:

• Language Identification (wiki article)