Update README.md

README.md

@@ -25,7 +25,8 @@ Vocal LLM is a joint audio-language model that bridges a frozen [Whisper](https:
 
 ## Architecture
 
-<img src="Joint_embedding_model_Sarvam_with_Whisper.svg" alt="Vocal LLM Architecture" width="100%">
+
+![Joint_embedding_model_Sarvam_with_Whisper](https://cdn-uploads.huggingface.co/production/uploads/666c3d6489e21df7d4a02805/hpryyOCYGnA3a5LD6BeZI.png)
 
 Vocal LLM consists of three components: