rohanrajpal/bert-base-en-hi-codemix-cased

The model was built using lingualytics, an open-source library that supports code-mixed analytics . It's a bert-base-multilingual-cased model from Huggingface and finetuned it on SAIL 2017 dataset . The training procedure is not the best, but this dataset is good, I will try to come up with a better training procedure! I am working on my own dataset and training procedure . The model is based on a model for Hinglish (cased) and has been used in PyTorch for the first time . The code is used to get the features of a given text in Pytorch . It can be used to,