audio_model_added

app.py

@@ -1,11 +1,12 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException,UploadFile,File
 from pydantic import BaseModel
 from deep_translator import GoogleTranslator
 from fastapi.responses import JSONResponse
-from main import process
+from main import process,audio_process
 # Create the FastAPI app instance
 app = FastAPI()
 
+
 # Root endpoint
 @app.get("/")
 async def home():
@@ -31,3 +32,14 @@ async def chatbot(text: str = ""):
     result = process(user_query=text)
     return {"result": result}
 
+@app.post("/audio_chat")
+async def chatbot(audio: UploadFile = File(...)):
+    if not audio:
+        raise HTTPException(status_code=400, detail="No audio file provided")
+
+    # Example of processing the audio file (you should replace `process` with your actual function)
+    try:
+        result = audio_process(audio.file)  # Replace with actual audio processing logic
+        return {"result": result}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"An error occurred: {str(e)}")

main.py

@@ -5,6 +5,7 @@ import random
 import pickle
 import os 
 from utils.rag import RAG
+from faster_whisper import WhisperModel
 
 
 # def dump_user_question(query):
@@ -43,9 +44,23 @@ def process(user_query:str):
     return final_output
 
 
+def audio_process(audio):
+    try:
+        model = WhisperModel("medium.en")
+        segments, info = model.transcribe(audio)
+        transcription = " ".join([seg.text for seg in segments])
+        result = process(user_query=transcription)
+        return result
+    except Exception as e:
+        print("Error:", e)
+        return str(e)
+
+
+
 
 if __name__ == "__main__":
-    pass
+    res = audio_process(r"C:\Users\lalit\Documents\Sound recordings\who_is_lalit.m4a")
+    print(res)
     # for _ in range(3):
     #     user = input("How can i help you :? \n")
     #     result = process(user)

requirements.txt

@@ -5,4 +5,5 @@ sentence_transformers
 langchain
 langchain-community
 langchain-google-genai
+faster_whisper