update readme

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 *.png filter=lfs diff=lfs merge=lfs -text
+google-cloud.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -98,11 +98,17 @@ User: "Thanks"
 "Great news! The Makani number 2871442438 is valid for the specified entrance in Dubai."
 ```
 
-## 🎯 Key Features
+## How we used Gemini and Pipecut?
 
-- **Parallel Tool Execution**: Handles multiple concurrent tool calls efficiently
-- **Graceful Waiting**: Provides user feedback while waiting for async results
-- **Natural Conversations**: Maintains conversational flow despite async operations
+### Gemini
+
+We used Gemini Speech to Text and are currently fine tuning Gemini 2.5 Flash Lite Model.
+
+![Google Cloud](./google-cloud.png)
+
+### Pipecat
+
+Link to implementation in Pipecat [Pull Request](https://github.com/pipecat-ai/pipecat/pull/2839).
 
 ## 🔧 Training Details