urduhack/roberta-urdu-small

Language model: roberta-urdu-small is a language model for urdu language . Training data was normalized using normalization module from Urduhack to eliminate characters from other languages like arabic . The training procedure was trained on urdu news corpus. The model was used to train data from a news corpus in Pakistan. The training data is normalized using a module from urduhack. The data was normalized using normalizations module from the NLP library to eliminate other languages such as Arabic and Arabic characters from the training data . The model is based on news data from Pakistan's Urdu news resources in the U.S. and other Pakistani languages. It has been trained,