mirror of
https://github.com/QuentinFuxa/WhisperLiveKit.git
synced 2026-03-07 22:33:36 +00:00
format html and change mapping id <-> speakers
This commit is contained in:
Quentin Fuxa
@@ -1,339 +1,361 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en">
|
||||
|
||||
<head>
|
||||
<meta charset="UTF-8"/>
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0"/>
|
||||
<title>Audio Transcription</title>
|
||||
<style>
|
||||
body {
|
||||
font-family: 'Inter', sans-serif;
|
||||
margin: 20px;
|
||||
text-align: center;
|
||||
}
|
||||
#recordButton {
|
||||
width: 80px;
|
||||
height: 80px;
|
||||
font-size: 36px;
|
||||
border: none;
|
||||
border-radius: 50%;
|
||||
background-color: white;
|
||||
cursor: pointer;
|
||||
box-shadow: 0 0px 10px rgba(0, 0, 0, 0.2);
|
||||
transition: background-color 0.3s ease, transform 0.2s ease;
|
||||
}
|
||||
#recordButton.recording {
|
||||
background-color: #ff4d4d;
|
||||
color: white;
|
||||
}
|
||||
#recordButton:active {
|
||||
transform: scale(0.95);
|
||||
}
|
||||
#status {
|
||||
margin-top: 20px;
|
||||
font-size: 16px;
|
||||
color: #333;
|
||||
}
|
||||
.settings-container {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
align-items: center;
|
||||
gap: 15px;
|
||||
margin-top: 20px;
|
||||
}
|
||||
.settings {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: flex-start;
|
||||
gap: 5px;
|
||||
}
|
||||
#chunkSelector,
|
||||
#websocketInput {
|
||||
font-size: 16px;
|
||||
padding: 5px;
|
||||
border-radius: 5px;
|
||||
border: 1px solid #ddd;
|
||||
background-color: #f9f9f9;
|
||||
}
|
||||
#websocketInput {
|
||||
width: 200px;
|
||||
}
|
||||
#chunkSelector:focus,
|
||||
#websocketInput:focus {
|
||||
outline: none;
|
||||
border-color: #007bff;
|
||||
}
|
||||
label {
|
||||
font-size: 14px;
|
||||
}
|
||||
/* Speaker-labeled transcript area */
|
||||
#linesTranscript {
|
||||
margin: 20px auto;
|
||||
max-width: 600px;
|
||||
text-align: left;
|
||||
font-size: 16px;
|
||||
}
|
||||
#linesTranscript p {
|
||||
margin: 5px 0;
|
||||
}
|
||||
#linesTranscript strong {
|
||||
color: #333;
|
||||
}
|
||||
#speaker {
|
||||
background-color: #dcefff;
|
||||
border-radius: 30px;
|
||||
padding: 2px 10px;
|
||||
font-size: 14px;
|
||||
}
|
||||
#timeInfo {
|
||||
color: #666;
|
||||
margin-left: 10px;
|
||||
}
|
||||
.textcontent {
|
||||
font-size: 16px;
|
||||
margin-left: 10px;
|
||||
padding-left: 10px;
|
||||
border-left: 2px solid #dcefff;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
.buffer {
|
||||
color: rgb(180, 180, 180);
|
||||
font-style: italic;
|
||||
margin-left: 4px;
|
||||
}
|
||||
.spinner {
|
||||
display: inline-block;
|
||||
width: 8px;
|
||||
height: 8px;
|
||||
border: 2px solid rgba(0, 0, 0, 0.2);
|
||||
border-top: 2px solid #333;
|
||||
border-radius: 50%;
|
||||
animation: spin 0.6s linear infinite;
|
||||
vertical-align: middle;
|
||||
margin-bottom: 2px;
|
||||
<meta charset="UTF-8" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||||
<title>Audio Transcription</title>
|
||||
<style>
|
||||
body {
|
||||
font-family: 'Inter', sans-serif;
|
||||
margin: 20px;
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
#recordButton {
|
||||
width: 80px;
|
||||
height: 80px;
|
||||
font-size: 36px;
|
||||
border: none;
|
||||
border-radius: 50%;
|
||||
background-color: white;
|
||||
cursor: pointer;
|
||||
box-shadow: 0 0px 10px rgba(0, 0, 0, 0.2);
|
||||
transition: background-color 0.3s ease, transform 0.2s ease;
|
||||
}
|
||||
|
||||
#recordButton.recording {
|
||||
background-color: #ff4d4d;
|
||||
color: white;
|
||||
}
|
||||
|
||||
#recordButton:active {
|
||||
transform: scale(0.95);
|
||||
}
|
||||
|
||||
#status {
|
||||
margin-top: 20px;
|
||||
font-size: 16px;
|
||||
color: #333;
|
||||
}
|
||||
|
||||
.settings-container {
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
align-items: center;
|
||||
gap: 15px;
|
||||
margin-top: 20px;
|
||||
}
|
||||
|
||||
.settings {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
align-items: flex-start;
|
||||
gap: 5px;
|
||||
}
|
||||
|
||||
#chunkSelector,
|
||||
#websocketInput {
|
||||
font-size: 16px;
|
||||
padding: 5px;
|
||||
border-radius: 5px;
|
||||
border: 1px solid #ddd;
|
||||
background-color: #f9f9f9;
|
||||
}
|
||||
|
||||
#websocketInput {
|
||||
width: 200px;
|
||||
}
|
||||
|
||||
#chunkSelector:focus,
|
||||
#websocketInput:focus {
|
||||
outline: none;
|
||||
border-color: #007bff;
|
||||
}
|
||||
|
||||
label {
|
||||
font-size: 14px;
|
||||
}
|
||||
|
||||
/* Speaker-labeled transcript area */
|
||||
#linesTranscript {
|
||||
margin: 20px auto;
|
||||
max-width: 600px;
|
||||
text-align: left;
|
||||
font-size: 16px;
|
||||
}
|
||||
|
||||
#linesTranscript p {
|
||||
margin: 5px 0;
|
||||
}
|
||||
|
||||
#linesTranscript strong {
|
||||
color: #333;
|
||||
}
|
||||
|
||||
#speaker {
|
||||
background-color: #dcefff;
|
||||
border-radius: 30px;
|
||||
padding: 2px 10px;
|
||||
font-size: 14px;
|
||||
}
|
||||
|
||||
#timeInfo {
|
||||
color: #666;
|
||||
margin-left: 10px;
|
||||
}
|
||||
|
||||
.textcontent {
|
||||
font-size: 16px;
|
||||
margin-left: 10px;
|
||||
padding-left: 10px;
|
||||
border-left: 2px solid #dcefff;
|
||||
margin-bottom: 10px;
|
||||
}
|
||||
|
||||
.buffer {
|
||||
color: rgb(180, 180, 180);
|
||||
font-style: italic;
|
||||
margin-left: 4px;
|
||||
}
|
||||
|
||||
.spinner {
|
||||
display: inline-block;
|
||||
width: 8px;
|
||||
height: 8px;
|
||||
border: 2px solid rgba(0, 0, 0, 0.2);
|
||||
border-top: 2px solid #333;
|
||||
border-radius: 50%;
|
||||
animation: spin 0.6s linear infinite;
|
||||
vertical-align: middle;
|
||||
margin-bottom: 2px;
|
||||
}
|
||||
|
||||
@keyframes spin {
|
||||
to {
|
||||
transform: rotate(360deg);
|
||||
to {
|
||||
transform: rotate(360deg);
|
||||
}
|
||||
}
|
||||
|
||||
.silence {
|
||||
color: #666;
|
||||
background-color: #f3f3f3;
|
||||
font-size: 13px;
|
||||
border-radius: 30px;
|
||||
padding: 2px 10px;
|
||||
}
|
||||
.silence {
|
||||
color: #666;
|
||||
background-color: #f3f3f3;
|
||||
font-size: 13px;
|
||||
border-radius: 30px;
|
||||
padding: 2px 10px;
|
||||
}
|
||||
.loading {
|
||||
color: #666;
|
||||
background-color: #eff9ff;
|
||||
font-size: 14px;
|
||||
border-radius: 30px;
|
||||
padding: 2px 10px;
|
||||
}
|
||||
</style>
|
||||
|
||||
.loading {
|
||||
color: #666;
|
||||
background-color: #eff9ff;
|
||||
font-size: 14px;
|
||||
border-radius: 30px;
|
||||
padding: 2px 10px;
|
||||
}
|
||||
</style>
|
||||
</head>
|
||||
|
||||
<body>
|
||||
|
||||
<div class="settings-container">
|
||||
<button id="recordButton">🎙️</button>
|
||||
<div class="settings">
|
||||
<div>
|
||||
<label for="chunkSelector">Chunk size (ms):</label>
|
||||
<select id="chunkSelector">
|
||||
<option value="500">500 ms</option>
|
||||
<option value="1000" selected>1000 ms</option>
|
||||
<option value="2000">2000 ms</option>
|
||||
<option value="3000">3000 ms</option>
|
||||
<option value="4000">4000 ms</option>
|
||||
<option value="5000">5000 ms</option>
|
||||
</select>
|
||||
</div>
|
||||
<div>
|
||||
<label for="websocketInput">WebSocket URL:</label>
|
||||
<input id="websocketInput" type="text" value="ws://localhost:8000/asr" />
|
||||
</div>
|
||||
<div class="settings-container">
|
||||
<button id="recordButton">🎙️</button>
|
||||
<div class="settings">
|
||||
<div>
|
||||
<label for="chunkSelector">Chunk size (ms):</label>
|
||||
<select id="chunkSelector">
|
||||
<option value="500">500 ms</option>
|
||||
<option value="1000" selected>1000 ms</option>
|
||||
<option value="2000">2000 ms</option>
|
||||
<option value="3000">3000 ms</option>
|
||||
<option value="4000">4000 ms</option>
|
||||
<option value="5000">5000 ms</option>
|
||||
</select>
|
||||
</div>
|
||||
<div>
|
||||
<label for="websocketInput">WebSocket URL:</label>
|
||||
<input id="websocketInput" type="text" value="ws://localhost:8000/asr" />
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<p id="status"></p>
|
||||
<p id="status"></p>
|
||||
|
||||
<!-- Speaker-labeled transcript -->
|
||||
<div id="linesTranscript"></div>
|
||||
<!-- Speaker-labeled transcript -->
|
||||
<div id="linesTranscript"></div>
|
||||
|
||||
<script>
|
||||
let isRecording = false;
|
||||
let websocket = null;
|
||||
let recorder = null;
|
||||
let chunkDuration = 1000;
|
||||
let websocketUrl = "ws://localhost:8000/asr";
|
||||
let userClosing = false;
|
||||
<script>
|
||||
let isRecording = false;
|
||||
let websocket = null;
|
||||
let recorder = null;
|
||||
let chunkDuration = 1000;
|
||||
let websocketUrl = "ws://localhost:8000/asr";
|
||||
let userClosing = false;
|
||||
|
||||
const statusText = document.getElementById("status");
|
||||
const recordButton = document.getElementById("recordButton");
|
||||
const chunkSelector = document.getElementById("chunkSelector");
|
||||
const websocketInput = document.getElementById("websocketInput");
|
||||
const linesTranscriptDiv = document.getElementById("linesTranscript");
|
||||
const statusText = document.getElementById("status");
|
||||
const recordButton = document.getElementById("recordButton");
|
||||
const chunkSelector = document.getElementById("chunkSelector");
|
||||
const websocketInput = document.getElementById("websocketInput");
|
||||
const linesTranscriptDiv = document.getElementById("linesTranscript");
|
||||
|
||||
chunkSelector.addEventListener("change", () => {
|
||||
chunkDuration = parseInt(chunkSelector.value);
|
||||
});
|
||||
chunkSelector.addEventListener("change", () => {
|
||||
chunkDuration = parseInt(chunkSelector.value);
|
||||
});
|
||||
|
||||
websocketInput.addEventListener("change", () => {
|
||||
const urlValue = websocketInput.value.trim();
|
||||
if (!urlValue.startsWith("ws://") && !urlValue.startsWith("wss://")) {
|
||||
statusText.textContent = "Invalid WebSocket URL (must start with ws:// or wss://)";
|
||||
return;
|
||||
}
|
||||
websocketUrl = urlValue;
|
||||
statusText.textContent = "WebSocket URL updated. Ready to connect.";
|
||||
});
|
||||
|
||||
function setupWebSocket() {
|
||||
return new Promise((resolve, reject) => {
|
||||
try {
|
||||
websocket = new WebSocket(websocketUrl);
|
||||
} catch (error) {
|
||||
statusText.textContent = "Invalid WebSocket URL. Please check and try again.";
|
||||
reject(error);
|
||||
return;
|
||||
}
|
||||
|
||||
websocket.onopen = () => {
|
||||
statusText.textContent = "Connected to server.";
|
||||
resolve();
|
||||
};
|
||||
|
||||
websocket.onclose = () => {
|
||||
if (userClosing) {
|
||||
statusText.textContent = "WebSocket closed by user.";
|
||||
} else {
|
||||
statusText.textContent =
|
||||
"Disconnected from the WebSocket server. (Check logs if model is loading.)";
|
||||
}
|
||||
userClosing = false;
|
||||
};
|
||||
|
||||
websocket.onerror = () => {
|
||||
statusText.textContent = "Error connecting to WebSocket.";
|
||||
reject(new Error("Error connecting to WebSocket"));
|
||||
};
|
||||
|
||||
// Handle messages from server
|
||||
websocket.onmessage = (event) => {
|
||||
const data = JSON.parse(event.data);
|
||||
/*
|
||||
The server might send:
|
||||
{
|
||||
"lines": [
|
||||
{"speaker": 0, "text": "Hello.", "beg": "00:00", "end": "00:01"},
|
||||
{"speaker": -2, "text": "Hi, no speaker here.", "beg": "00:01", "end": "00:02"},
|
||||
{"speaker": -1, "text": "...", "beg": "00:02", "end": "00:03" },
|
||||
...
|
||||
],
|
||||
"buffer": "..."
|
||||
websocketInput.addEventListener("change", () => {
|
||||
const urlValue = websocketInput.value.trim();
|
||||
if (!urlValue.startsWith("ws://") && !urlValue.startsWith("wss://")) {
|
||||
statusText.textContent = "Invalid WebSocket URL (must start with ws:// or wss://)";
|
||||
return;
|
||||
}
|
||||
*/
|
||||
const { lines = [], buffer = "" } = data;
|
||||
renderLinesWithBuffer( lines, buffer);
|
||||
};
|
||||
});
|
||||
}
|
||||
websocketUrl = urlValue;
|
||||
statusText.textContent = "WebSocket URL updated. Ready to connect.";
|
||||
});
|
||||
|
||||
function renderLinesWithBuffer(lines, buffer) {
|
||||
// Clears if no lines
|
||||
if (!Array.isArray(lines) || lines.length === 0) {
|
||||
linesTranscriptDiv.innerHTML = "";
|
||||
return;
|
||||
}
|
||||
function setupWebSocket() {
|
||||
return new Promise((resolve, reject) => {
|
||||
try {
|
||||
websocket = new WebSocket(websocketUrl);
|
||||
} catch (error) {
|
||||
statusText.textContent = "Invalid WebSocket URL. Please check and try again.";
|
||||
reject(error);
|
||||
return;
|
||||
}
|
||||
|
||||
websocket.onopen = () => {
|
||||
statusText.textContent = "Connected to server.";
|
||||
resolve();
|
||||
};
|
||||
|
||||
websocket.onclose = () => {
|
||||
if (userClosing) {
|
||||
statusText.textContent = "WebSocket closed by user.";
|
||||
} else {
|
||||
statusText.textContent =
|
||||
"Disconnected from the WebSocket server. (Check logs if model is loading.)";
|
||||
}
|
||||
userClosing = false;
|
||||
};
|
||||
|
||||
const linesHtml = lines.map((item, idx) => {
|
||||
let timeInfo = "";
|
||||
if (item.beg !== undefined && item.end !== undefined) {
|
||||
timeInfo = ` ${item.beg} - ${item.end}`;
|
||||
websocket.onerror = () => {
|
||||
statusText.textContent = "Error connecting to WebSocket.";
|
||||
reject(new Error("Error connecting to WebSocket"));
|
||||
};
|
||||
|
||||
// Handle messages from server
|
||||
websocket.onmessage = (event) => {
|
||||
const data = JSON.parse(event.data);
|
||||
/*
|
||||
The server might send:
|
||||
{
|
||||
"lines": [
|
||||
{"speaker": 0, "text": "Hello.", "beg": "00:00", "end": "00:01"},
|
||||
{"speaker": -2, "text": "Hi, no speaker here.", "beg": "00:01", "end": "00:02"},
|
||||
{"speaker": -1, "text": "...", "beg": "00:02", "end": "00:03" },
|
||||
...
|
||||
],
|
||||
"buffer": "..."
|
||||
}
|
||||
*/
|
||||
const { lines = [], buffer = "" } = data;
|
||||
renderLinesWithBuffer(lines, buffer);
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
let speakerLabel = "";
|
||||
if (item.speaker === -2) {
|
||||
speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
|
||||
} else if (item.speaker == -1) {
|
||||
speakerLabel = `<span class='loading'> <span class="spinner"></span><span id='timeInfo'>${item.diff} second(s) of audio are undergoing diarization</span></span>`;
|
||||
} else if (item.speaker == -3) {
|
||||
speakerLabel = `<span id="speaker"><span id='timeInfo'>${timeInfo}</span>`;
|
||||
} else if (item.speaker !== -1) {
|
||||
speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
|
||||
}
|
||||
|
||||
function renderLinesWithBuffer(lines, buffer) {
|
||||
if (!Array.isArray(lines) || lines.length === 0) {
|
||||
if (buffer) {
|
||||
linesTranscriptDiv.innerHTML = `<span class="buffer">${buffer}</span>`;
|
||||
} else {
|
||||
linesTranscriptDiv.innerHTML = "";
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
|
||||
let textContent = item.text;
|
||||
if (idx === lines.length - 1 && buffer) {
|
||||
textContent += `<span class="buffer">${buffer}</span>`;
|
||||
const linesHtml = lines.map((item, idx) => {
|
||||
let timeInfo = "";
|
||||
if (item.beg !== undefined && item.end !== undefined) {
|
||||
timeInfo = ` ${item.beg} - ${item.end}`;
|
||||
}
|
||||
|
||||
let speakerLabel = "";
|
||||
if (item.speaker === -2) {
|
||||
speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
|
||||
} else if (item.speaker == 0) {
|
||||
speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'>${item.diff} second(s) of audio are undergoing diarization</span></span>`;
|
||||
} else if (item.speaker == -1) {
|
||||
speakerLabel = `<span id="speaker"><span id='timeInfo'>${timeInfo}</span>`;
|
||||
} else if (item.speaker !== -1) {
|
||||
speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
|
||||
}
|
||||
|
||||
let textContent = item.text;
|
||||
if (idx === lines.length - 1 && buffer) {
|
||||
textContent += `<span class="buffer">${buffer}</span>`;
|
||||
}
|
||||
|
||||
return textContent
|
||||
? `<p>${speakerLabel}<br/><div class='textcontent'>${textContent}</div></p>`
|
||||
: `<p>${speakerLabel}<br/></p>`;
|
||||
}).join("");
|
||||
|
||||
linesTranscriptDiv.innerHTML = linesHtml;
|
||||
}
|
||||
|
||||
return textContent
|
||||
? `<p>${speakerLabel}<br/><div class='textcontent'>${textContent}</div></p>`
|
||||
: `<p >${speakerLabel}<br/></p>`;
|
||||
}).join("");
|
||||
|
||||
linesTranscriptDiv.innerHTML = linesHtml;
|
||||
}
|
||||
|
||||
async function startRecording() {
|
||||
try {
|
||||
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
|
||||
recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
|
||||
recorder.ondataavailable = (e) => {
|
||||
if (websocket && websocket.readyState === WebSocket.OPEN) {
|
||||
websocket.send(e.data);
|
||||
}
|
||||
};
|
||||
recorder.start(chunkDuration);
|
||||
isRecording = true;
|
||||
updateUI();
|
||||
} catch (err) {
|
||||
statusText.textContent = "Error accessing microphone. Please allow microphone access.";
|
||||
}
|
||||
}
|
||||
|
||||
function stopRecording() {
|
||||
userClosing = true;
|
||||
if (recorder) {
|
||||
recorder.stop();
|
||||
recorder = null;
|
||||
}
|
||||
isRecording = false;
|
||||
|
||||
if (websocket) {
|
||||
websocket.close();
|
||||
websocket = null;
|
||||
}
|
||||
|
||||
updateUI();
|
||||
}
|
||||
|
||||
async function toggleRecording() {
|
||||
if (!isRecording) {
|
||||
linesTranscriptDiv.innerHTML = "";
|
||||
try {
|
||||
await setupWebSocket();
|
||||
await startRecording();
|
||||
} catch (err) {
|
||||
statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
|
||||
async function startRecording() {
|
||||
try {
|
||||
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
|
||||
recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
|
||||
recorder.ondataavailable = (e) => {
|
||||
if (websocket && websocket.readyState === WebSocket.OPEN) {
|
||||
websocket.send(e.data);
|
||||
}
|
||||
};
|
||||
recorder.start(chunkDuration);
|
||||
isRecording = true;
|
||||
updateUI();
|
||||
} catch (err) {
|
||||
statusText.textContent = "Error accessing microphone. Please allow microphone access.";
|
||||
}
|
||||
}
|
||||
} else {
|
||||
stopRecording();
|
||||
}
|
||||
}
|
||||
|
||||
function updateUI() {
|
||||
recordButton.classList.toggle("recording", isRecording);
|
||||
statusText.textContent = isRecording ? "Recording..." : "Click to start transcription";
|
||||
}
|
||||
function stopRecording() {
|
||||
userClosing = true;
|
||||
if (recorder) {
|
||||
recorder.stop();
|
||||
recorder = null;
|
||||
}
|
||||
isRecording = false;
|
||||
|
||||
recordButton.addEventListener("click", toggleRecording);
|
||||
</script>
|
||||
if (websocket) {
|
||||
websocket.close();
|
||||
websocket = null;
|
||||
}
|
||||
|
||||
updateUI();
|
||||
}
|
||||
|
||||
async function toggleRecording() {
|
||||
if (!isRecording) {
|
||||
linesTranscriptDiv.innerHTML = "";
|
||||
try {
|
||||
await setupWebSocket();
|
||||
await startRecording();
|
||||
} catch (err) {
|
||||
statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
|
||||
}
|
||||
} else {
|
||||
stopRecording();
|
||||
}
|
||||
}
|
||||
|
||||
function updateUI() {
|
||||
recordButton.classList.toggle("recording", isRecording);
|
||||
statusText.textContent = isRecording ? "Recording..." : "Click to start transcription";
|
||||
}
|
||||
|
||||
recordButton.addEventListener("click", toggleRecording);
|
||||
</script>
|
||||
</body>
|
||||
|
||||
</html>
|
||||
Reference in New Issue
Block a user