py3langid
py3langid copied to clipboard
bad case: print(identifier.classify("开会。")) , output:('ja', 0.97436696). except: ('zh', 1.0)
bad case:
print(identifier.classify("开会。")) ,
output:('ja', 0.97436696).
except: ('zh', 1.0)
When the input string is too short is it more difficult to guess but there is indeed an issue here, simplified Chinese characters are obviously not Japanese.