Create app.py

app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import speech_recognition as sr
+import pyttsx3
+from transformers import pipeline
+
+# Initialize recognizer for speech recognition
+recognizer = sr.Recognizer()
+
+# Initialize text-to-speech engine
+engine = pyttsx3.init()
+
+# Initialize Hugging Face NLP pipeline for intent recognition
+nlp = pipeline("zero-shot-classification")
+
+# Define the food menu
+menu = {
+    'Pizza': ['Cheese', 'Pepperoni', 'Vegetarian'],
+    'Beverages': ['Coke', 'Pepsi', 'Water']
+}
+
+# Function to process the order
+def process_order(order):
+    if 'pizza' in order.lower():
+        return "What type of pizza would you like? Cheese, Pepperoni, or Vegetarian?"
+    elif 'coke' in order.lower():
+        return "One Coke added to your order."
+    else:
+        return "Sorry, we didn't catch that. Please try again."
+
+# Function to handle speech recognition
+def recognize_speech(audio):
+    try:
+        text = recognizer.recognize_google(audio)
+        response = process_order(text)
+        engine.say(response)  # TTS response
+        engine.runAndWait()
+        return response
+    except Exception as e:
+        return "Sorry, I could not understand."
+
+# Gradio Interface for the app
+def create_gradio_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("## AI Voice Bot for Food Ordering")
+
+        # Speech-to-Text: User speaks into microphone
+        audio_input = gr.Audio(source="microphone", type="numpy", label="Speak to the bot")
+
+        # Display the bot's response after recognition
+        output_text = gr.Textbox(label="Bot Response")
+
+        # Define the button to process the audio input
+        audio_input.change(fn=recognize_speech, inputs=audio_input, outputs=output_text)
+
+    return demo
+
+# Create and launch the Gradio app
+if __name__ == "__main__":
+    app = create_gradio_interface()
+    app.launch(share=True)