File size: 8,231 Bytes
408a4d8
a843dd5
5e1848a
 
a843dd5
 
 
408a4d8
a843dd5
408a4d8
 
a843dd5
 
408a4d8
a843dd5
408a4d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a843dd5
408a4d8
 
 
 
 
 
 
a843dd5
 
 
 
 
 
 
408a4d8
a843dd5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
408a4d8
 
 
 
 
 
 
 
 
 
 
 
a843dd5
 
 
 
 
 
5e1848a
a843dd5
 
 
 
 
 
30e1c24
a843dd5
 
 
 
 
 
 
 
 
30e1c24
a843dd5
408a4d8
30e1c24
408a4d8
 
a843dd5
408a4d8
30e1c24
5e1848a
a843dd5
 
 
 
 
408a4d8
a843dd5
408a4d8
 
a843dd5
 
 
 
 
 
 
 
 
 
408a4d8
 
 
 
a843dd5
 
 
 
 
 
26eed15
a843dd5
 
 
 
408a4d8
 
a011d11
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
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
from flask import Flask, render_template_string, request, jsonify
import speech_recognition as sr
from tempfile import NamedTemporaryFile
import os
import ffmpeg
import logging
from werkzeug.exceptions import BadRequest

# Initialize Flask App
app = Flask(__name__)

# Set up logging
logging.basicConfig(level=logging.INFO)

# HTML Template for Frontend
html_code = """
<!DOCTYPE html>
<html lang="en">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>AI Dining Assistant</title>
    <style>
        body {
            font-family: Arial, sans-serif;
            background-color: #f4f4f9;
            display: flex;
            flex-direction: column;
            align-items: center;
            justify-content: center;
            height: 100vh;
            margin: 0;
        }
        h1 {
            color: #333;
        }
        .mic-button {
            width: 80px;
            height: 80px;
            border-radius: 50%;
            background-color: #007bff;
            color: white;
            font-size: 24px;
            border: none;
            display: flex;
            align-items: center;
            justify-content: center;
            cursor: pointer;
            box-shadow: 0px 4px 6px rgba(0, 0, 0, 0.1);
            transition: background-color 0.3s;
        }
        .mic-button:hover {
            background-color: #0056b3;
        }
        .status {
            margin-top: 20px;
            font-size: 18px;
            color: #666;
        }
        .listening {
            color: green;
            font-weight: bold;
        }
        .response {
            margin-top: 20px;
            padding: 10px;
            background-color: #fff;
            border: 1px solid #ddd;
            border-radius: 5px;
            box-shadow: 0px 4px 6px rgba(0, 0, 0, 0.1);
            width: 300px;
            text-align: center;
        }
    </style>
</head>
<body>
    <h1>AI Dining Assistant</h1>
    <button class="mic-button" id="mic-button">🎤</button>
    <div class="status" id="status">Press the mic button to start the conversation...</div>
    <div class="response" id="response" style="display: none;">Response will appear here...</div>
    <script>
        const micButton = document.getElementById('mic-button');
        const status = document.getElementById('status');
        const response = document.getElementById('response');
        let mediaRecorder;
        let audioChunks = [];
        let isConversationActive = false;

        micButton.addEventListener('click', () => {
            if (!isConversationActive) {
                isConversationActive = true;
                startConversation();
            }
        });

        function startConversation() {
            status.textContent = 'Listening...';
            startListening();
        }

        function startListening() {
            navigator.mediaDevices.getUserMedia({ audio: true }).then(stream => {
                mediaRecorder = new MediaRecorder(stream, { mimeType: 'audio/webm;codecs=opus' });
                mediaRecorder.start();
                audioChunks = [];
                mediaRecorder.ondataavailable = event => audioChunks.push(event.data);
                mediaRecorder.onstop = async () => {
                    const audioBlob = new Blob(audioChunks, { type: 'audio/webm' });
                    const formData = new FormData();
                    formData.append('audio', audioBlob);

                    status.textContent = 'Processing...';
                    try {
                        const result = await fetch('/process-audio', { method: 'POST', body: formData });
                        const data = await result.json();
                        response.textContent = data.response;
                        response.style.display = 'block';

                        const utterance = new SpeechSynthesisUtterance(data.response);
                        speechSynthesis.speak(utterance);

                        if (data.response.includes("Goodbye")) {
                            status.textContent = 'Conversation ended. Press the mic button to start again.';
                            isConversationActive = false;
                        } else {
                            status.textContent = 'Listening...';
                            setTimeout(startListening, 1000); // Continue listening
                        }
                    } catch (error) {
                        response.textContent = 'Error occurred. Please try again.';
                        response.style.display = 'block';
                        status.textContent = 'Press the mic button to restart the conversation.';
                        isConversationActive = false;
                    }
                };
                setTimeout(() => mediaRecorder.stop(), 5000); // Stop recording after 5 seconds
            }).catch(() => {
                status.textContent = 'Microphone access denied.';
                isConversationActive = false;
            });
        }
    </script>
</body>
</html>
"""

@app.route('/')
def index():
    return render_template_string(html_code)

@app.route('/process-audio', methods=['POST'])
def process_audio():
    try:
        # Validate audio file
        audio_file = request.files.get('audio')
        if not audio_file:
            raise BadRequest("No audio file provided.")

        temp_file = NamedTemporaryFile(delete=False, suffix=".webm")
        audio_file.save(temp_file.name)
        logging.info(f"Saved input audio to {temp_file.name}")

        if os.path.getsize(temp_file.name) == 0:
            raise BadRequest("Uploaded audio file is empty.")

        # Convert audio to PCM WAV format
        converted_file = NamedTemporaryFile(delete=False, suffix=".wav")
        try:
            ffmpeg.input(temp_file.name).output(
                converted_file.name, acodec='pcm_s16le', ac=1, ar='16000'
            ).run(overwrite_output=True)
        except Exception as ffmpeg_error:
            logging.error(f"FFmpeg conversion error: {str(ffmpeg_error)}")
            return jsonify({"response": "Audio conversion failed. Please try again."})

        logging.info(f"Converted audio saved to {converted_file.name}")

        # Recognize speech
        recognizer = sr.Recognizer()
        with sr.AudioFile(converted_file.name) as source:
            audio_data = recognizer.record(source)
            command = recognizer.recognize_google(audio_data)
            logging.info(f"Recognized command: {command}")
            response = process_command(command)

        return jsonify({"response": response})

    except BadRequest as br:
        logging.error(f"Bad request error: {br}")
        return jsonify({"response": f"Bad Request: {str(br)}"})

    except Exception as e:
        logging.error(f"Error processing audio: {e}")
        return jsonify({"response": f"An error occurred: {str(e)}"})

    finally:
        # Clean up temporary files
        try:
            if os.path.exists(temp_file.name):
                os.unlink(temp_file.name)
            if os.path.exists(converted_file.name):
                os.unlink(converted_file.name)
        except Exception as cleanup_error:
            logging.error(f"Error cleaning up files: {cleanup_error}")

def process_command(command):
    """Process the user's voice command and return a response."""
    command = command.lower()
    if "menu" in command:
        return (
            "Here is our menu: "
            "South Indian dishes include Idli, Dosa, Vada, Pongal, Biryani, and Sambar Rice. "
            "North Indian dishes include Butter Chicken, Paneer Butter Masala, Naan, Dal Makhani, Chole Bhature, and Rajma Chawal. "
            "What would you like to order?"
        )
    elif "order" in command:
        return "Your order has been placed. Would you like anything else?"
    elif "no" in command or "nothing" in command:
        return "Goodbye! Thank you for using AI Dining Assistant."
    return "Sorry, I didn't understand your request. Please ask about the menu or place an order."

if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860)