Update model descriptions

README.md

@@ -6,6 +6,12 @@ This model contains just the `IPUConfig` files for running the HuBERT-base model
 
 **This model contains no model weights, only an IPUConfig.** 
 
+## Model description
+HUBERT (Hidden-Unit BERT) is a BERT-based model for self-supervised speech representation learning approach that relies on predicting K-means cluster assignments of masked segments of continuous output. This approach forces the model to learn a combined acoustic and language model over the continuous inputs by applying the prediction loss over the masked region. 
+
+Paper link : [Self-Supervised Speech Representation
+Learning by Masked Prediction of Hidden Unit](https://arxiv.org/pdf/2106.07447v1.pdf)
+
 ## Usage
 
 ```