app.py

import gradio as gr
import speech_recognition as sr
from gtts import gTTS
import os
import pygame  # Use pygame for playing audio
from transformers import pipeline

# Initialize pygame for audio playback
pygame.mixer.init()

# Initialize recognizer for speech recognition
recognizer = sr.Recognizer()

# Initialize Hugging Face NLP pipeline for intent recognition using a specific model
nlp = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")

# 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 from audio files or microphone
def recognize_speech(audio):
    try:
        # If audio is from file, use SpeechRecognition to convert speech to text
        if isinstance(audio, str):  # Audio file input (filepath)
            with sr.AudioFile(audio) as source:
                audio_data = recognizer.record(source)
                text = recognizer.recognize_google(audio_data)
        else:  # Audio from microphone input
            text = recognizer.recognize_google(audio)
        
        print(f"Recognized text: {text}")  # Print the recognized text for debugging
        
        response = process_order(text)

        # Using gTTS to respond back with speech
        tts = gTTS(text=response, lang='en')
        tts.save("response.mp3")
        
        # Play the MP3 response using pygame
        pygame.mixer.music.load("response.mp3")
        pygame.mixer.music.play()

        return response
    except Exception as e:
        print(f"Error: {e}")  # Print the error for debugging
        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")

        # Audio Input: User speaks into microphone or uploads a file (filepath)
        audio_input = gr.Audio(type="filepath", label="Speak to the bot (Upload or Record Audio)")

        # 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)