format html and change mapping id <-> speakers

This commit is contained in:
Quentin Fuxa 2025-02-23 23:13:18 +01:00
parent f200f2cad4
commit 34b707d84e

View file

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