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

The bert-base-multilingual-cased model was built using lingualytics, an open-source library that supports code-mixed analytics . Since I dont know spanish, I cant verify the quality of the annotations or the dataset itself . This is a simple transfer learning approach and I'm open to discussions to improve upon this . Make sure to preprocess your data using these methods before using this model . The model was trained on the CS-EN-ES-CORPUS dataset . The training procedure was followed by the pre-processing techniques followed here . The results were evaluated using the BertTokenizer, BertModelForSequenceClassification and TensorFlow .,