Update README.md

README.md

@@ -33,10 +33,10 @@ Ground truth text with prosody encoding and ASR encoding residual cross attentio
 
 ## Model description
 
-ASR encoder: [Whisper small](https://huggingface.co/openai/whisper-small) encoder
-Prosody encoder: 2 layer transformer encoder with initial dense projection
+ASR encoder: [Whisper small](https://huggingface.co/openai/whisper-small) encoder  
+Prosody encoder: 2 layer transformer encoder with initial dense projection  
 Backbone: [DistilBert uncased](https://huggingface.co/distilbert/distilbert-base-uncased)  
-Fusion: 2 residual cross attention fusion layers (F_asr x F_text and F_prosody x F_text) with dense layer on top
+Fusion: 2 residual cross attention fusion layers (F_asr x F_text and F_prosody x F_text) with dense layer on top  
 Pooling: Self attention  
 Multi-label classification head: 2 dense layers with two dropouts 0.3 and Tanh activation inbetween