Update README.md

README.md

@@ -20,8 +20,10 @@ tags:
 - new
 ---
 
-### NLP/ASR model with acoustic variable radii relative position embedding (vRoPE) that maps pitch to token. 
-----
+
+<img width="670" alt="3t" src="https://github.com/user-attachments/assets/4158ead2-75f4-42e2-84f8-7b39b6984026"  />
+
+NLP/ASR multimodal pitch aware model. 
 
 Pitch-Aware Processing: Integrates F0/pitch information throughout the processing pipeline, making the model sensitive to prosodic features of speech.
 
@@ -110,4 +112,3 @@ The theoretical foundation:
 
 --- 
 
-<img width="470" alt="cc2" src="https://github.com/user-attachments/assets/d52a48b1-8717-4d29-9452-cfdf43c92fe8"  />