Spaces:
Sleeping
Sleeping
import streamlit as st | |
import datetime | |
import os | |
import base64 | |
# Initialize session state variables | |
if 'transcript_history' not in st.session_state: | |
st.session_state.transcript_history = [] | |
# Function to create a download link for a string | |
def get_download_link(text, filename): | |
b64 = base64.b64encode(text.encode()).decode() | |
return f'<a href="data:text/plain;base64,{b64}" download="{filename}">Download Transcript</a>' | |
# Create the main layout | |
st.title("Speech Recognition with Transcript History") | |
col1, col2 = st.columns([2, 1]) | |
with col1: | |
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> | |
<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; | |
// Function to start recognition | |
const startRecognition = () => { | |
try { | |
recognition.start(); | |
status.textContent = 'Listening...'; | |
startButton.disabled = true; | |
stopButton.disabled = false; | |
} catch (e) { | |
console.error(e); | |
status.textContent = 'Error: ' + e.message; | |
} | |
}; | |
// Auto-start on load | |
window.addEventListener('load', () => { | |
setTimeout(startRecognition, 1000); // Delay start by 1 second to ensure everything is loaded | |
}); | |
startButton.onclick = startRecognition; | |
stopButton.onclick = () => { | |
recognition.stop(); | |
status.textContent = 'Stopped'; | |
startButton.disabled = false; | |
stopButton.disabled = true; | |
}; | |
clearButton.onclick = () => { | |
fullTranscript = ''; | |
output.textContent = ''; | |
// Send clear signal to Streamlit | |
window.parent.postMessage({type: 'clear'}, '*'); | |
}; | |
recognition.onresult = (event) => { | |
let interimTranscript = ''; | |
let finalTranscript = ''; | |
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; | |
} | |
} | |
if (finalTranscript || (Date.now() - lastUpdateTime > 5000)) { | |
if (finalTranscript) { | |
fullTranscript += finalTranscript; | |
// Send to Streamlit | |
window.parent.postMessage({ | |
type: 'transcript', | |
text: finalTranscript | |
}, '*'); | |
} | |
lastUpdateTime = Date.now(); | |
} | |
output.textContent = fullTranscript + (interimTranscript ? '... ' + interimTranscript : ''); | |
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; | |
} | |
}; | |
// Listen for messages from Streamlit | |
window.addEventListener('message', (event) => { | |
if (event.data.type === 'clear') { | |
fullTranscript = ''; | |
output.textContent = ''; | |
} | |
}); | |
} | |
</script> | |
</body> | |
</html> | |
""" | |
# Display the HTML component | |
component = st.components.v1.html(html, height=400) | |
with col2: | |
# Display transcript history | |
st.subheader("Transcript History") | |
# Function to save transcript | |
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, 'w', encoding='utf-8') as f: | |
f.write(text) | |
return filename | |
# Display transcript | |
if st.session_state.transcript_history: | |
full_transcript = "\n".join(st.session_state.transcript_history) | |
st.text_area("Full Transcript", value=full_transcript, height=300) | |
# Save transcript to file | |
timestamp = datetime.datetime.now().strftime('%Y%m%d_%H%M%S') | |
filename = f"transcript_{timestamp}.md" | |
# Create download link | |
st.markdown(get_download_link(full_transcript, filename), unsafe_allow_html=True) | |
# Save to file system | |
if st.button("Save to File"): | |
saved_file = save_transcript(full_transcript) | |
st.success(f"Saved to {saved_file}") | |
# Handle transcript updates from JavaScript | |
if component: | |
try: | |
data = component | |
if isinstance(data, dict) and data.get('type') == 'transcript': | |
st.session_state.transcript_history.append(data['text']) | |
st.experimental_rerun() | |
elif isinstance(data, dict) and data.get('type') == 'clear': | |
st.session_state.transcript_history = [] | |
st.experimental_rerun() | |
except Exception as e: | |
st.error(f"Error processing transcript: {e}") |