Text Classification
Transformers
Safetensors
bert
lid
Language Identification
African Languages
Inference Endpoints
ThapeloAndrewSindane commited on
Commit
1244426
1 Parent(s): 41650c4

This Model Performs Language Identification for all South African languages (Sepedi (nso), Sesotho(sot), Setswana(tsn), Xitsonga(tso), Isindebele(nr), Tshivenda(ven), IsiXhosa(xho), IsiZulu(zul), IsiSwati(ssw), Afrikaans(af), and English(en)).
The source data used to train the model came from the paper 'Preparing Vuk...' referenced below:

# Model:
The model used is a bert model trained to detect all 11 South African languages.


# References

* Lastrucci, R., Dzingirai, I., Rajab, J., Madodonga, A., Shingange, M., Njini, D. and Marivate, V., 2023. Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora. arXiv preprint arXiv:2303.03750.

Files changed (1) hide show
  1. README.md +10 -0
README.md ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ This Model Performs Language Identification for all South African languages (Sepedi (nso), Sesotho(sot), Setswana(tsn), Xitsonga(tso), Isindebele(nr), Tshivenda(ven), IsiXhosa(xho), IsiZulu(zul), IsiSwati(ssw), Afrikaans(af), and English(en)).
2
+ The source data used to train the model came from the paper 'Preparing Vuk...' referenced below:
3
+
4
+ # Model:
5
+ The model used is a bert model trained to detect all 11 South African languages.
6
+
7
+
8
+ # References
9
+
10
+ * Lastrucci, R., Dzingirai, I., Rajab, J., Madodonga, A., Shingange, M., Njini, D. and Marivate, V., 2023. Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora. arXiv preprint arXiv:2303.03750.