Update README.md

README.md

@@ -10,9 +10,9 @@ SparQLe (Speech Routing to Query LLMs) enables direct speech-to-text understandi
 
 **Key strengths:**
 
-* **Preserves semantic content** of spoken input in the produced text ([arXiv][2])
-* **Efficiently leverages frozen SSL models**, avoiding heavy ASR backbones like Whisper ([arXiv][3])
-* **Modular design** with a query‑former (Q‑former) adapter and LLM backend ([GitHub][4])
+* **Preserves semantic content** of spoken input in the produced text
+* **Efficiently leverages frozen SSL models**, avoiding heavy ASR backbones like Whisper
+* **Modular design** with a query‑former (Q‑former) adapter and LLM backend
 
 **Architecture:**