File size: 6,927 Bytes
f43e9df
 
 
8cf2c43
f43e9df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
972ecb5
 
f43e9df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
972ecb5
 
f43e9df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
972ecb5
8cf2c43
f43e9df
 
972ecb5
 
 
 
 
 
 
 
 
 
 
f43e9df
972ecb5
 
 
f43e9df
 
 
 
 
 
 
 
 
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
import streamlit as st
import datetime
import os
import json

# Initialize session state for transcript history if not exists
if 'transcript_history' not in st.session_state:
    st.session_state.transcript_history = ""

# Create a container for the transcript history
history_container = st.empty()
text_area = st.empty()

html = """
<!DOCTYPE html>
<html>
<head>
    <title>Continuous Speech Demo</title>
    <style>
        body { 
            font-family: sans-serif; 
            padding: 20px; 
            max-width: 800px;
            margin: 0 auto;
        }
        button { 
            padding: 10px 20px; 
            margin: 10px 5px;
            font-size: 16px;
        }
        #status { 
            margin: 10px 0;
            padding: 10px;
            background: #e8f5e9;
            border-radius: 4px;
        }
        #output {
            white-space: pre-wrap;
            padding: 15px;
            background: #f5f5f5;
            border-radius: 4px;
            margin: 10px 0;
            min-height: 100px;
            max-height: 400px;
            overflow-y: auto;
        }
        .controls {
            margin: 10px 0;
        }
    </style>
</head>
<body>
    <h1>Continuous Speech Recognition</h1>
    <div class="controls">
        <button id="start">Start Listening</button>
        <button id="stop" disabled>Stop Listening</button>
        <button id="clear">Clear Text</button>
    </div>
    <div id="status">Ready</div>
    <div id="output"></div>

    <script>
        if (!('webkitSpeechRecognition' in window)) {
            alert('Speech recognition not supported');
        } else {
            const recognition = new webkitSpeechRecognition();
            const startButton = document.getElementById('start');
            const stopButton = document.getElementById('stop');
            const clearButton = document.getElementById('clear');
            const status = document.getElementById('status');
            const output = document.getElementById('output');
            let fullTranscript = '';
            let lastUpdateTime = Date.now();

            // Configure recognition
            recognition.continuous = true;
            recognition.interimResults = true;

            startButton.onclick = () => {
                try {
                    recognition.start();
                    status.textContent = 'Listening...';
                    startButton.disabled = true;
                    stopButton.disabled = false;
                } catch (e) {
                    console.error(e);
                    status.textContent = 'Error: ' + e.message;
                }
            };

            stopButton.onclick = () => {
                recognition.stop();
                status.textContent = 'Stopped';
                startButton.disabled = false;
                stopButton.disabled = true;
            };

            clearButton.onclick = () => {
                fullTranscript = '';
                output.textContent = '';
                // Send empty string to Streamlit
                window.Streamlit.setComponentValue('');
            };

            recognition.onresult = (event) => {
                let interimTranscript = '';
                let finalTranscript = '';

                // Process results
                for (let i = event.resultIndex; i < event.results.length; i++) {
                    const transcript = event.results[i][0].transcript;
                    if (event.results[i].isFinal) {
                        finalTranscript += transcript + '\\n';
                    } else {
                        interimTranscript += transcript;
                    }
                }

                // Update if we have final results or it's been 5 seconds
                if (finalTranscript || (Date.now() - lastUpdateTime > 5000)) {
                    if (finalTranscript) {
                        fullTranscript += finalTranscript;
                        // Send final transcript to Streamlit
                        window.Streamlit.setComponentValue(finalTranscript);
                    }
                    lastUpdateTime = Date.now();
                }

                // Display results
                output.textContent = fullTranscript + (interimTranscript ? '... ' + interimTranscript : '');
                
                // Auto-scroll to bottom
                output.scrollTop = output.scrollHeight;
            };

            recognition.onend = () => {
                if (!stopButton.disabled) {
                    try {
                        recognition.start();
                        console.log('Restarted recognition');
                    } catch (e) {
                        console.error('Failed to restart recognition:', e);
                        status.textContent = 'Error restarting: ' + e.message;
                        startButton.disabled = false;
                        stopButton.disabled = true;
                    }
                }
            };

            recognition.onerror = (event) => {
                console.error('Recognition error:', event.error);
                status.textContent = 'Error: ' + event.error;
                
                if (event.error === 'not-allowed' || event.error === 'service-not-allowed') {
                    startButton.disabled = false;
                    stopButton.disabled = true;
                }
            };
        }
    </script>
</body>
</html>
"""

# Function to save transcript to file
def save_transcript(text):
    if not os.path.exists('transcripts'):
        os.makedirs('transcripts')
    
    timestamp = datetime.datetime.now().strftime('%Y%m%d_%H%M%S')
    filename = f"transcripts/transcript_{timestamp}.md"
    
    with open(filename, 'a', encoding='utf-8') as f:
        f.write(text + '\n')

# Main app
st.title("Speech Recognition with Transcript History")

# Create custom component and get its value
component_value = st.components.v1.html(html, height=600)

# If we receive a new transcript
if component_value:
    # The component_value will be the direct transcript text
    new_text = str(component_value)
    
    # Only process non-empty transcripts
    if new_text.strip():
        # Update the transcript history
        st.session_state.transcript_history += new_text
        
        # Save to file
        save_transcript(new_text)
        
        # Update the display
        history_container.markdown(st.session_state.transcript_history)
        text_area.text_area("Full Transcript", st.session_state.transcript_history, height=200)

# Add a download button for the full transcript
if st.session_state.transcript_history:
    st.download_button(
        label="Download Full Transcript",
        data=st.session_state.transcript_history,
        file_name=f"transcript_{datetime.datetime.now().strftime('%Y%m%d_%H%M%S')}.md",
        mime="text/markdown"
    )