Language Identifier (LID) is a tool to automatically classify a text document by line or document as one of the eleven official South African languages.
Evaluation of LID:
(In-house evaluation)
Language
Document level F-score
Line level F-score
Afrikaans
0.99
English
isiNdebele
0.95
isiXhosa
0.97
isiZulu
0.98
Sesotho sa Leboa
Sesotho
Setswana
SiSwati
Tshivenḓa
1.0
Xitsonga