End of transcription : Properly sends signal back to the endpoint

This commit is contained in:
Quentin Fuxa 2025-05-07 10:55:12 +02:00
parent bc7c32100f
commit 8e4674b093

View file

@ -308,6 +308,7 @@
let waveCtx = waveCanvas.getContext("2d"); let waveCtx = waveCanvas.getContext("2d");
let animationFrame = null; let animationFrame = null;
let waitingForStop = false; let waitingForStop = false;
let lastReceivedData = null;
waveCanvas.width = 60 * (window.devicePixelRatio || 1); waveCanvas.width = 60 * (window.devicePixelRatio || 1);
waveCanvas.height = 30 * (window.devicePixelRatio || 1); waveCanvas.height = 30 * (window.devicePixelRatio || 1);
waveCtx.scale(window.devicePixelRatio || 1, window.devicePixelRatio || 1); waveCtx.scale(window.devicePixelRatio || 1, window.devicePixelRatio || 1);
@ -357,18 +358,31 @@
websocket.onclose = () => { websocket.onclose = () => {
if (userClosing) { if (userClosing) {
if (!statusText.textContent.includes("Recording stopped. Processing final audio")) { // This is a bit of a hack. We should have a better way to handle this. eg. using a status code. if (waitingForStop) {
statusText.textContent = "Finished processing audio! Ready to record again."; statusText.textContent = "Processing finalized or connection closed.";
if (lastReceivedData) {
renderLinesWithBuffer(
lastReceivedData.lines || [],
lastReceivedData.buffer_diarization || "",
lastReceivedData.buffer_transcription || "",
0, 0, true // isFinalizing = true
);
}
} }
waitingForStop = false; // If ready_to_stop was received, statusText is already "Finished processing..."
// and waitingForStop is false.
} else { } else {
statusText.textContent = statusText.textContent = "Disconnected from the WebSocket server. (Check logs if model is loading.)";
"Disconnected from the WebSocket server. (Check logs if model is loading.)";
if (isRecording) { if (isRecording) {
stopRecording(); stopRecording();
} }
} }
userClosing = false; isRecording = false;
waitingForStop = false;
userClosing = false;
lastReceivedData = null;
websocket = null;
updateUI();
}; };
websocket.onerror = () => { websocket.onerror = () => {
@ -382,24 +396,31 @@
// Check for status messages // Check for status messages
if (data.type === "ready_to_stop") { if (data.type === "ready_to_stop") {
console.log("Ready to stop, closing WebSocket"); console.log("Ready to stop received, finalizing display and closing WebSocket.");
// signal that we are not waiting for stop anymore
waitingForStop = false; waitingForStop = false;
recordButton.disabled = false; // this should be elsewhere
console.log("Record button enabled");
//Now we can close the WebSocket if (lastReceivedData) {
if (websocket) { renderLinesWithBuffer(
websocket.close(); lastReceivedData.lines || [],
websocket = null; lastReceivedData.buffer_diarization || "",
lastReceivedData.buffer_transcription || "",
0, // No more lag
0, // No more lag
true // isFinalizing = true
);
} }
statusText.textContent = "Finished processing audio! Ready to record again.";
recordButton.disabled = false;
if (websocket) {
websocket.close(); // will trigger onclose
// websocket = null; // onclose handle setting websocket to null
}
return; return;
} }
lastReceivedData = data;
// Handle normal transcription updates // Handle normal transcription updates
const { const {
lines = [], lines = [],
@ -414,13 +435,14 @@
buffer_diarization, buffer_diarization,
buffer_transcription, buffer_transcription,
remaining_time_diarization, remaining_time_diarization,
remaining_time_transcription remaining_time_transcription,
false // isFinalizing = false for normal updates
); );
}; };
}); });
} }
function renderLinesWithBuffer(lines, buffer_diarization, buffer_transcription, remaining_time_diarization, remaining_time_transcription) { function renderLinesWithBuffer(lines, buffer_diarization, buffer_transcription, remaining_time_diarization, remaining_time_transcription, isFinalizing = false) {
const linesHtml = lines.map((item, idx) => { const linesHtml = lines.map((item, idx) => {
let timeInfo = ""; let timeInfo = "";
if (item.beg !== undefined && item.end !== undefined) { if (item.beg !== undefined && item.end !== undefined) {
@ -430,30 +452,46 @@
let speakerLabel = ""; let speakerLabel = "";
if (item.speaker === -2) { if (item.speaker === -2) {
speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`; speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
} else if (item.speaker == 0) { } else if (item.speaker == 0 && !isFinalizing) {
speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'>${remaining_time_diarization} second(s) of audio are undergoing diarization</span></span>`; speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'>${remaining_time_diarization} second(s) of audio are undergoing diarization</span></span>`;
} else if (item.speaker == -1) { } else if (item.speaker == -1) {
speakerLabel = `<span id="speaker"><span id='timeInfo'>${timeInfo}</span></span>`; speakerLabel = `<span id="speaker">Speaker 1<span id='timeInfo'>${timeInfo}</span></span>`;
} else if (item.speaker !== -1) { } else if (item.speaker !== -1 && item.speaker !== 0) {
speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`; speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
} }
let textContent = item.text;
if (idx === lines.length - 1) { let currentLineText = item.text || "";
speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Transcription lag <span id='timeInfo'>${remaining_time_transcription}s</span></span>`
} if (idx === lines.length - 1) {
if (idx === lines.length - 1 && buffer_diarization) { if (!isFinalizing) {
speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Diarization lag<span id='timeInfo'>${remaining_time_diarization}s</span></span>` if (remaining_time_transcription > 0) {
textContent += `<span class="buffer_diarization">${buffer_diarization}</span>`; speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Transcription lag <span id='timeInfo'>${remaining_time_transcription}s</span></span>`;
} }
if (idx === lines.length - 1) { if (buffer_diarization && remaining_time_diarization > 0) {
textContent += `<span class="buffer_transcription">${buffer_transcription}</span>`; speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Diarization lag<span id='timeInfo'>${remaining_time_diarization}s</span></span>`;
}
}
if (buffer_diarization) {
if (isFinalizing) {
currentLineText += (currentLineText.length > 0 && buffer_diarization.trim().length > 0 ? " " : "") + buffer_diarization.trim();
} else {
currentLineText += `<span class="buffer_diarization">${buffer_diarization}</span>`;
}
}
if (buffer_transcription) {
if (isFinalizing) {
currentLineText += (currentLineText.length > 0 && buffer_transcription.trim().length > 0 ? " " : "") + buffer_transcription.trim();
} else {
currentLineText += `<span class="buffer_transcription">${buffer_transcription}</span>`;
}
}
} }
return currentLineText.trim().length > 0 || speakerLabel.length > 0
return textContent ? `<p>${speakerLabel}<br/><div class='textcontent'>${currentLineText}</div></p>`
? `<p>${speakerLabel}<br/><div class='textcontent'>${textContent}</div></p>` : `<p>${speakerLabel}<br/></p>`;
: `<p>${speakerLabel}<br/></p>`;
}).join(""); }).join("");
linesTranscriptDiv.innerHTML = linesHtml; linesTranscriptDiv.innerHTML = linesHtml;
@ -578,20 +616,6 @@
timerElement.textContent = "00:00"; timerElement.textContent = "00:00";
startTime = null; startTime = null;
if (websocket && websocket.readyState === WebSocket.OPEN) {
try {
await websocket.send(JSON.stringify({
type: "stop",
message: "User stopped recording"
}));
statusText.textContent = "Recording stopped. Processing final audio...";
} catch (e) {
console.error("Could not send stop message:", e);
statusText.textContent = "Recording stopped. Error during final audio processing.";
websocket.close();
websocket = null;
}
}
isRecording = false; isRecording = false;
updateUI(); updateUI();
@ -625,19 +649,22 @@
function updateUI() { function updateUI() {
recordButton.classList.toggle("recording", isRecording); recordButton.classList.toggle("recording", isRecording);
recordButton.disabled = waitingForStop;
if (waitingForStop) { if (waitingForStop) {
statusText.textContent = "Please wait for processing to complete..."; if (statusText.textContent !== "Recording stopped. Processing final audio...") {
recordButton.disabled = true; // Optionally disable the button while waiting statusText.textContent = "Please wait for processing to complete...";
console.log("Record button disabled"); }
} else if (isRecording) { } else if (isRecording) {
statusText.textContent = "Recording..."; statusText.textContent = "Recording...";
recordButton.disabled = false;
console.log("Record button enabled");
} else { } else {
statusText.textContent = "Click to start transcription"; if (statusText.textContent !== "Finished processing audio! Ready to record again." &&
statusText.textContent !== "Processing finalized or connection closed.") {
statusText.textContent = "Click to start transcription";
}
}
if (!waitingForStop) {
recordButton.disabled = false; recordButton.disabled = false;
console.log("Record button enabled");
} }
} }
@ -645,4 +672,4 @@
</script> </script>
</body> </body>
</html> </html>