Update app.py

app.py

@@ -1,44 +1,71 @@
-import openai
-import pyttsx3  # TTS
+import gradio as gr
+import pyttsx3
 from transformers import pipeline
-from speech_recognition import Recognizer, Microphone
+import whisper
 
-# Initialize TTS engine
+# Initialize Whisper Model
+model = whisper.load_model("base")
+
+# Initialize Text-to-Speech
 engine = pyttsx3.init()
 
-# Speech recognition
-recognizer = Recognizer()
+# Load NLP Model
+nlp_pipeline = pipeline("text-classification", model="distilbert-base-uncased-finetuned-sst-2-english")
+
+# Define Menu
+MENU = {
+    "biryani": 200,
+    "naan": 50,
+    "curry": 150,
+    "paneer": 180,
+    "samosa": 20,
+}
+
+# Speech-to-Text Function
+def speech_to_text(audio):
+    try:
+        audio_path = audio
+        result = model.transcribe(audio_path)
+        return result["text"]
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# NLP Intent Detection
+def process_order(transcription):
+    items = []
+    total_cost = 0
 
-def listen():
-    with Microphone() as source:
-        print("Listening...")
-        audio = recognizer.listen(source)
-        return recognizer.recognize_google(audio)
+    for item in MENU.keys():
+        if item in transcription.lower():
+            items.append(item)
+            total_cost += MENU[item]
 
-def process_order(text):
-    # Sample NLP pipeline
-    menu = {"chicken biryani": 200, "garlic naan": 50, "paneer curry": 150}
-    order = [item for item in menu if item in text.lower()]
-    total = sum(menu[item] for item in order)
-    return order, total
+    if items:
+        response = f"You've ordered: {', '.join(items)}. Total cost is ₹{total_cost}."
+    else:
+        response = "Sorry, I could not find any menu items in your order."
 
-def speak(response):
+    # Text-to-Speech for Response
     engine.say(response)
     engine.runAndWait()
+    return response
 
-# Main loop
-print("Voice ordering system for blind individuals.")
-speak("Welcome to our restaurant. Please place your order.")
-while True:
-    try:
-        user_input = listen()
-        items, total = process_order(user_input)
-        if items:
-            response = f"You've ordered {', '.join(items)}. Total is {total}."
-            print(response)
-            speak(response)
-            speak("Say confirm to place your order or cancel to restart.")
-        else:
-            speak("I couldn't find that on the menu. Please try again.")
-    except Exception as e:
-        speak("Sorry, I didn't catch that. Please repeat.")
+# Gradio Interface
+def order_from_audio(audio):
+    transcription = speech_to_text(audio)
+    return transcription, process_order(transcription)
+
+# Gradio UI
+app = gr.Interface(
+    fn=order_from_audio,
+    inputs=gr.Audio(source="microphone", type="filepath"),
+    outputs=[
+        gr.Textbox(label="Transcription"),
+        gr.Textbox(label="Order Confirmation"),
+    ],
+    title="Voice Ordering System",
+    description="Speak your order, and the system will process it.",
+)
+
+if __name__ == "__main__":
+    app.launch()