Update model description

README.md

@@ -6,6 +6,12 @@ This model contains just the `IPUConfig` files for running the Wav2Vec2 base mod
 
 **This model contains no model weights, only an IPUConfig.** 
 
+## Model description
+From [wav2vec 2.0: A Framework for Self-Supervised
+Learning of Speech Representations](https://arxiv.org/pdf/2006.11477v3.pdf),  
+
+“Wave2vec2 is a framework for self-supervised learning of speech representations. It masks the speech input in the latent space and solves a contrastive task defined over a quantization of the latent representations which are jointly learned.” 
+
 ## Usage
 
 ```