Based on great work on the london map, trying to recreate this for my local town.
According to CENSUS, Greek is 2nd most spoken language at home, but had 2 in 40k results returned as Greek...

If I enter a clear phrase into Google Translate, and get the greek output, and then throw this at CLD, it never seems to be able to get it right.

>>> cld.detect("Σήμερα ο καιρός είναι ζεστός", pickSummaryLanguage=False, removeWeakMatches=True)
('RUSSIAN', 'ru', True, 22, [('RUSSIAN', 'ru', 31, 1.303780964797914)])