Spaces:

langtech-innovation
/

WhisperLiveKitDiarization

Paused

File size: 24,570 Bytes

<!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: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
            margin: 20px;
            text-align: center;
        }

        #recordButton {
            width: 50px;
            height: 50px;
            border: none;
            border-radius: 50%;
            background-color: white;
            cursor: pointer;
            transition: all 0.3s ease;
            border: 1px solid rgb(233, 233, 233);
            display: flex;
            align-items: center;
            justify-content: center;
            position: relative;
        }

        #recordButton.recording {
            width: 180px;
            border-radius: 40px;
            justify-content: flex-start;
            padding-left: 20px;
        }

        #recordButton:active {
            transform: scale(0.95);
        }

        .shape-container {
            width: 25px;
            height: 25px;
            display: flex;
            align-items: center;
            justify-content: center;
            flex-shrink: 0;
        }

        .shape {
            width: 25px;
            height: 25px;
            background-color: rgb(209, 61, 53);
            border-radius: 50%;
            transition: all 0.3s ease;
        }

        #recordButton:disabled .shape {
            background-color: #6e6d6d;
        }

        #recordButton.recording .shape {
            border-radius: 5px;
            width: 25px;
            height: 25px;
        }

        /* Recording elements */
        .recording-info {
            display: none;
            align-items: center;
            margin-left: 15px;
            flex-grow: 1;
        }

        #recordButton.recording .recording-info {
            display: flex;
        }

        .wave-container {
            width: 60px;
            height: 30px;
            position: relative;
            display: flex;
            align-items: center;
            justify-content: center;
        }

        #waveCanvas {
            width: 100%;
            height: 100%;
        }

        .timer {
            font-size: 14px;
            font-weight: 500;
            color: #333;
            margin-left: 10px;
        }

        #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: #ffffff;
            max-height: 30px;
        }

        #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: 700px;
            text-align: left;
            font-size: 16px;
        }

        #linesTranscript p {
            margin: 0px 0;
        }

        #linesTranscript strong {
            color: #333;
        }

        #speaker {
            border: 1px solid rgb(229, 229, 229);
            border-radius: 100px;
            padding: 2px 10px;
            font-size: 14px;
            margin-bottom: 0px;
        }
        .label_diarization {
            background-color: #ffffff66;
            border-radius: 8px 8px 8px 8px;
            padding: 2px 10px;
            margin-left: 10px;
            display: inline-block;
            white-space: nowrap;
            font-size: 14px;
            margin-bottom: 0px;
            color: rgb(134, 134, 134)
        }

        .label_transcription {
            background-color: #ffffff66;
            border-radius: 8px 8px 8px 8px;
            padding: 2px 10px;
            display: inline-block;
            white-space: nowrap;
            margin-left: 10px;
            font-size: 14px;
            margin-bottom: 0px;
            color: #000000
        }

        #timeInfo {
            color: #666;
            margin-left: 10px;
        }

        .textcontent {
            font-size: 16px;
            /* margin-left: 10px; */
            padding-left: 10px;
            margin-bottom: 10px;
            margin-top: 1px;
            padding-top: 5px;
            border-radius: 0px 0px 0px 10px;
        }

        .buffer_diarization {
            color: rgb(134, 134, 134);
            margin-left: 4px;
        }

        .buffer_transcription {
            color: #7474748c;
            margin-left: 4px;
        }


        .spinner {
            display: inline-block;
            width: 8px;
            height: 8px;
            border: 2px solid #8d8d8d5c;
            border-top: 2px solid #6c6c6ce5;
            border-radius: 50%;
            animation: spin 0.6s linear infinite;
            vertical-align: middle;
            margin-bottom: 2px;
            margin-right: 5px;
        }

        @keyframes spin {
            to {
                transform: rotate(360deg);
            }
        }

        .silence {
            color: #666;
            background-color: #f3f3f3;
            font-size: 13px;
            border-radius: 30px;
            padding: 2px 10px;
        }

        .loading {
            color: #666;
            background-color: #ff4d4d0f;
            border-radius: 8px 8px 8px 0px;
            padding: 2px 10px;
            font-size: 14px;
            margin-bottom: 0px;
        }
    </style>
</head>

<body>

    <div class="settings-container">
        <button id="recordButton">
            <div class="shape-container">
                <div class="shape"></div>
            </div>
            <div class="recording-info">
                <div class="wave-container">
                    <canvas id="waveCanvas"></canvas>
                </div>
                <div class="timer">00:00</div>
            </div>
        </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" />
            </div>
        </div>
    </div>

    <p id="status"></p>

    <!-- 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;
        let startTime = null;
        let timerInterval = null;
        let audioContext = null;
        let analyser = null;
        let microphone = null;
        let waveCanvas = document.getElementById("waveCanvas");
        let waveCtx = waveCanvas.getContext("2d");
        let animationFrame = null;
        let waitingForStop = false;
        let lastReceivedData = null;
        waveCanvas.width = 60 * (window.devicePixelRatio || 1);
        waveCanvas.height = 30 * (window.devicePixelRatio || 1);
        waveCtx.scale(window.devicePixelRatio || 1, window.devicePixelRatio || 1);

        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 timerElement = document.querySelector(".timer");

        const host = window.location.hostname || "localhost";
        const port = window.location.port || "8000";
        const protocol = window.location.protocol === "https:" ? "wss" : "ws";
        const defaultWebSocketUrl = `${protocol}://${host}:${port}/asr`;
        websocketInput.value = defaultWebSocketUrl;
        websocketUrl = defaultWebSocketUrl;

        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) {
                        if (waitingForStop) {
                            statusText.textContent = "Processing finalized or connection closed.";
                            if (lastReceivedData) {
                                renderLinesWithBuffer(
                                    lastReceivedData.lines || [],
                                    lastReceivedData.buffer_diarization || "",
                                    lastReceivedData.buffer_transcription || "",
                                    0, 0, true // isFinalizing = true
                                );
                            }
                        }
                        // If ready_to_stop was received, statusText is already "Finished processing..."
                        // and waitingForStop is false.
                    } else {
                        statusText.textContent = "Disconnected from the WebSocket server. (Check logs if model is loading.)";
                        if (isRecording) {
                            stopRecording(); 
                        }
                    }
                    isRecording = false;  
                    waitingForStop = false; 
                    userClosing = false;  
                    lastReceivedData = null;  
                    websocket = null;    
                    updateUI();  
                };

                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);
                    
                    // Check for status messages
                    if (data.type === "ready_to_stop") {
                        console.log("Ready to stop received, finalizing display and closing WebSocket.");
                        waitingForStop = false;

                        if (lastReceivedData) {
                            renderLinesWithBuffer(
                                lastReceivedData.lines || [],
                                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;
                    }
                    
                    lastReceivedData = data; 
                    
                    // Handle normal transcription updates
                    const { 
                        lines = [], 
                        buffer_transcription = "", 
                        buffer_diarization = "",
                        remaining_time_transcription = 0,
                        remaining_time_diarization = 0,
                        status = "active_transcription"
                    } = data;
                    
                    renderLinesWithBuffer(
                        lines, 
                        buffer_diarization, 
                        buffer_transcription, 
                        remaining_time_diarization,
                        remaining_time_transcription,
                        false,
                        status
                    );
                };
            });
        }

        function renderLinesWithBuffer(lines, buffer_diarization, buffer_transcription, remaining_time_diarization, remaining_time_transcription, isFinalizing = false, current_status = "active_transcription") {
            if (current_status === "no_audio_detected") {
                linesTranscriptDiv.innerHTML = "<p style='text-align: center; color: #666; margin-top: 20px;'><em>No audio detected...</em></p>";
                return; 
            }

            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'>${timeInfo}</span></span>`;
                } else if (item.speaker == 0 && !isFinalizing) {
                    speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'>${remaining_time_diarization} second(s) of audio are undergoing diarization</span></span>`;
                } else if (item.speaker == -1) {
                    speakerLabel = `<span id="speaker">Speaker 1<span id='timeInfo'>${timeInfo}</span></span>`;
                } else if (item.speaker !== -1 && item.speaker !== 0) {
                    speakerLabel = `<span id="speaker">Speaker ${item.speaker}<span id='timeInfo'>${timeInfo}</span></span>`;
                }


                let currentLineText = item.text || "";

                if (idx === lines.length - 1) { 
                    if (!isFinalizing) {
                        if (remaining_time_transcription > 0) {
                             speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Transcription lag <span id='timeInfo'>${remaining_time_transcription}s</span></span>`;
                        }
                        if (buffer_diarization && remaining_time_diarization > 0) {
                             speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Diarization lag<span id='timeInfo'>${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
                    ? `<p>${speakerLabel}<br/><div class='textcontent'>${currentLineText}</div></p>`
                    : `<p>${speakerLabel}<br/></p>`; 
            }).join("");

            linesTranscriptDiv.innerHTML = linesHtml;
        }

        function updateTimer() {
            if (!startTime) return;
            
            const elapsed = Math.floor((Date.now() - startTime) / 1000);
            const minutes = Math.floor(elapsed / 60).toString().padStart(2, "0");
            const seconds = (elapsed % 60).toString().padStart(2, "0");
            timerElement.textContent = `${minutes}:${seconds}`;
        }

        function drawWaveform() {
            if (!analyser) return;
            
            const bufferLength = analyser.frequencyBinCount;
            const dataArray = new Uint8Array(bufferLength);
            analyser.getByteTimeDomainData(dataArray);
            
            waveCtx.clearRect(0, 0, waveCanvas.width / (window.devicePixelRatio || 1), waveCanvas.height / (window.devicePixelRatio || 1));
            waveCtx.lineWidth = 1;
            waveCtx.strokeStyle = 'rgb(0, 0, 0)';
            waveCtx.beginPath();
            
            const sliceWidth = (waveCanvas.width / (window.devicePixelRatio || 1)) / bufferLength;
            let x = 0;
            
            for (let i = 0; i < bufferLength; i++) {
                const v = dataArray[i] / 128.0;
                const y = v * (waveCanvas.height / (window.devicePixelRatio || 1)) / 2;
                
                if (i === 0) {
                    waveCtx.moveTo(x, y);
                } else {
                    waveCtx.lineTo(x, y);
                }
                
                x += sliceWidth;
            }
            
            waveCtx.lineTo(waveCanvas.width / (window.devicePixelRatio || 1), waveCanvas.height / (window.devicePixelRatio || 1) / 2);
            waveCtx.stroke();
            
            animationFrame = requestAnimationFrame(drawWaveform);
        }

        async function startRecording() {
            try {
                const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
                
                audioContext = new (window.AudioContext || window.webkitAudioContext)();
                analyser = audioContext.createAnalyser();
                analyser.fftSize = 256;
                microphone = audioContext.createMediaStreamSource(stream);
                microphone.connect(analyser);
                
                recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
                recorder.ondataavailable = (e) => {
                    if (websocket && websocket.readyState === WebSocket.OPEN) {
                        websocket.send(e.data);
                    }
                };
                recorder.start(chunkDuration);
                
                startTime = Date.now();
                timerInterval = setInterval(updateTimer, 1000);
                drawWaveform();
                
                isRecording = true;
                updateUI();
            } catch (err) {
                statusText.textContent = "Error accessing microphone. Please allow microphone access.";
                console.error(err);
            }
        }

        async function stopRecording() {
            userClosing = true;
            waitingForStop = true;
            
            if (websocket && websocket.readyState === WebSocket.OPEN) {
                // Send empty audio buffer as stop signal
                const emptyBlob = new Blob([], { type: 'audio/webm' });
                websocket.send(emptyBlob);
                statusText.textContent = "Recording stopped. Processing final audio...";
            }
            
            if (recorder) {
                recorder.stop();
                recorder = null;
            }
            
            if (microphone) {
                microphone.disconnect();
                microphone = null;
            }
            
            if (analyser) {
                analyser = null;
            }
            
            if (audioContext && audioContext.state !== 'closed') {
                try {
                    audioContext.close();
                } catch (e) {
                    console.warn("Could not close audio context:", e);
                }
                audioContext = null;
            }
            
            if (animationFrame) {
                cancelAnimationFrame(animationFrame);
                animationFrame = null;
            }
            
            if (timerInterval) {
                clearInterval(timerInterval);
                timerInterval = null;
            }            
            timerElement.textContent = "00:00";
            startTime = null;
            
            
            isRecording = false;
            updateUI();	
        }

        async function toggleRecording() {
            if (!isRecording) {
                if (waitingForStop) {
                    console.log("Waiting for stop, early return");
                    return;  // Early return, UI is already updated
                }
                console.log("Connecting to WebSocket");
                try {
                    // If we have an active WebSocket that's still processing, just restart audio capture
                    if (websocket && websocket.readyState === WebSocket.OPEN) {
                        await startRecording();
                    } else {
                        // If no active WebSocket or it's closed, create new one
                        await setupWebSocket();
                        await startRecording();
                    }
                } catch (err) {
                    statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
                    console.error(err);
                }
            } else {
                console.log("Stopping recording");
                stopRecording();
            }
        }

        function updateUI() {
            recordButton.classList.toggle("recording", isRecording);
            recordButton.disabled = waitingForStop;

            if (waitingForStop) {
                if (statusText.textContent !== "Recording stopped. Processing final audio...") {
                     statusText.textContent = "Please wait for processing to complete...";
                }
            } else if (isRecording) {
                statusText.textContent = "Recording...";
            } else {
                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.addEventListener("click", toggleRecording);
    </script>
</body>

</html>