File size: 2,092 Bytes
a992697
 
f1d3292
 
b6e0bda
a992697
 
 
 
 
1ed992a
 
a992697
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ed992a
a992697
 
f1d3292
 
 
 
b6e0bda
 
 
f1d3292
a992697
 
 
 
 
 
 
 
 
1ed992a
c218b1a
a992697
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
import gradio as gr
import speech_recognition as sr
from gtts import gTTS
import os
from playsound import playsound  # Import playsound library
from transformers import pipeline

# 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
def recognize_speech(audio):
    try:
        # Recognize speech using SpeechRecognition
        text = recognizer.recognize_google(audio)
        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 playsound
        playsound("response.mp3")

        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")

        # Audio Input: User speaks into microphone
        audio_input = gr.Audio(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)