bump to 0.2.12

fix wss for reverse proxying

README.md

@@ -54,7 +54,15 @@ pip install whisperlivekit
 > - See [tokenizer.py](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py) for the list of all available languages.
 > - For HTTPS requirements, see the **Parameters** section for SSL configuration options.
 
- 
+#### Use it to capture audio from web pages.
+
+Go to `chrome-extension` for instructions.
+
+<p align="center">
+<img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/chrome-extension/demo-extension.png" alt="WhisperLiveKit Demo" width="600">
+</p>
+
+
 
 #### Optional Dependencies
 
@@ -132,6 +140,7 @@ async def websocket_endpoint(websocket: WebSocket):
 | Parameter | Description | Default |
 |-----------|-------------|---------|
 | `--model` | Whisper model size. List and recommandations [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/available_models.md) | `small` |
+| `--model-dir` | Directory containing Whisper model.bin and other files. Overrides `--model`. | `None` |
 | `--language` | List [here](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/simul_whisper/whisper/tokenizer.py). If you use `auto`, the model attempts to detect the language automatically, but it tends to bias towards English. | `auto` |
 | `--target-language` | If sets, activates translation using NLLB. Ex: `fr`. [118 languages available](https://github.com/QuentinFuxa/WhisperLiveKit/blob/main/whisperlivekit/translation/mapping_languages.py). If you want to translate to english, you should rather use `--task translate`, since Whisper can do it directly. | `None` |
 | `--task` | Set to `translate` to translate *only* to english, using Whisper translation. | `transcribe` |
@@ -144,6 +153,7 @@ async def websocket_endpoint(websocket: WebSocket):
 | `--port` | Server port | `8000` |
 | `--ssl-certfile` | Path to the SSL certificate file (for HTTPS support) | `None` |
 | `--ssl-keyfile` | Path to the SSL private key file (for HTTPS support) | `None` |
+| `--forwarded-allow-ips` | Ip or Ips allowed to reverse proxy the whisperlivekit-server. Supported types are  IP Addresses (e.g. 127.0.0.1), IP Networks (e.g. 10.100.0.0/16), or Literals (e.g. /path/to/socket.sock) | `None` |
 | `--pcm-input` | raw PCM (s16le) data is expected as input and FFmpeg will be bypassed. Frontend will use AudioWorklet instead of MediaRecorder | `False` |
 
 | Translation options | Description | Default |
@@ -161,6 +171,7 @@ async def websocket_endpoint(websocket: WebSocket):
 | SimulStreaming backend options | Description | Default |
 |-----------|-------------|---------|
 | `--disable-fast-encoder` | Disable Faster Whisper or MLX Whisper backends for the encoder (if installed). Inference can be slower but helpful when GPU memory is limited | `False` |
+| `--custom-alignment-heads` | Use your own alignment heads, useful when `--model-dir` is used | `None` |
 | `--frame-threshold` | AlignAtt frame threshold (lower = faster, higher = more accurate) | `25` |
 | `--beams` | Number of beams for beam search (1 = greedy decoding) | `1` |
 | `--decoder` | Force decoder type (`beam` or `greedy`) | `auto` |

chrome-extension/README.md

@@ -1,11 +1,13 @@
-## WhisperLiveKit Chrome Extension v0.1.0
+## WhisperLiveKit Chrome Extension v0.1.1
-Capture the audio of your current tab, transcribe or translate it using WhisperliveKit. **Still unstable**
+Capture the audio of your current tab, transcribe diarize and translate it using WhisperliveKit, in Chrome and other Chromium-based browsers.
+
+> Currently, only the tab audio is captured; your microphone audio is not recorded.
 
 <img src="https://raw.githubusercontent.com/QuentinFuxa/WhisperLiveKit/refs/heads/main/chrome-extension/demo-extension.png" alt="WhisperLiveKit Demo" width="730">
 
 ## Running this extension
-1. Clone this repository.
+1. Run `python sync_extension.py` to copy frontend files to the `chrome-extension` directory.
-2. Load this directory in Chrome as an unpacked extension.
+2. Load the `chrome-extension` directory in Chrome as an unpacked extension.
 
 
 ## Devs:

chrome-extension/live_transcription.js

@@ -1,669 +0,0 @@
-/* Theme, WebSocket, recording, rendering logic extracted from inline script and adapted for segmented theme control and WS caption */
-let isRecording = false;
-let websocket = null;
-let recorder = null;
-let chunkDuration = 100;
-let websocketUrl = "ws://localhost:8000/asr";
-let userClosing = false;
-let wakeLock = null;
-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;
-let lastSignature = null;
-let availableMicrophones = [];
-let selectedMicrophoneId = 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 websocketDefaultSpan = document.getElementById("wsDefaultUrl");
-const linesTranscriptDiv = document.getElementById("linesTranscript");
-const timerElement = document.querySelector(".timer");
-const themeRadios = document.querySelectorAll('input[name="theme"]');
-const microphoneSelect = document.getElementById("microphoneSelect");
-const settingsToggle = document.getElementById("settingsToggle");
-const settingsDiv = document.querySelector(".settings");
-
-
-
-chrome.runtime.onInstalled.addListener((details) => {
-    if (details.reason.search(/install/g) === -1) {
-        return
-    }
-    chrome.tabs.create({
-        url: chrome.runtime.getURL("welcome.html"),
-        active: true
-    })
-})
-
-function getWaveStroke() {
-  const styles = getComputedStyle(document.documentElement);
-  const v = styles.getPropertyValue("--wave-stroke").trim();
-  return v || "#000";
-}
-
-let waveStroke = getWaveStroke();
-function updateWaveStroke() {
-  waveStroke = getWaveStroke();
-}
-
-function applyTheme(pref) {
-  if (pref === "light") {
-    document.documentElement.setAttribute("data-theme", "light");
-  } else if (pref === "dark") {
-    document.documentElement.setAttribute("data-theme", "dark");
-  } else {
-    document.documentElement.removeAttribute("data-theme");
-  }
-  updateWaveStroke();
-}
-
-// Persisted theme preference
-const savedThemePref = localStorage.getItem("themePreference") || "system";
-applyTheme(savedThemePref);
-if (themeRadios.length) {
-  themeRadios.forEach((r) => {
-    r.checked = r.value === savedThemePref;
-    r.addEventListener("change", () => {
-      if (r.checked) {
-        localStorage.setItem("themePreference", r.value);
-        applyTheme(r.value);
-      }
-    });
-  });
-}
-
-// React to OS theme changes when in "system" mode
-const darkMq = window.matchMedia && window.matchMedia("(prefers-color-scheme: dark)");
-const handleOsThemeChange = () => {
-  const pref = localStorage.getItem("themePreference") || "system";
-  if (pref === "system") updateWaveStroke();
-};
-if (darkMq && darkMq.addEventListener) {
-  darkMq.addEventListener("change", handleOsThemeChange);
-} else if (darkMq && darkMq.addListener) {
-  // deprecated, but included for Safari compatibility
-  darkMq.addListener(handleOsThemeChange);
-}
-
-async function enumerateMicrophones() {
-  try {
-      const micPermission = await navigator.permissions.query({
-    name: "microphone",
-  });
-  
-    const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
-    stream.getTracks().forEach(track => track.stop());
-
-    const devices = await navigator.mediaDevices.enumerateDevices();
-    availableMicrophones = devices.filter(device => device.kind === 'audioinput');
-
-    populateMicrophoneSelect();
-    console.log(`Found ${availableMicrophones.length} microphone(s)`);
-  } catch (error) {
-    console.error('Error enumerating microphones:', error);
-    statusText.textContent = "Error accessing microphones. Please grant permission.";
-  }
-}
-
-function populateMicrophoneSelect() {
-  if (!microphoneSelect) return;
-
-  microphoneSelect.innerHTML = '<option value="">Default Microphone</option>';
-
-  availableMicrophones.forEach((device, index) => {
-    const option = document.createElement('option');
-    option.value = device.deviceId;
-    option.textContent = device.label || `Microphone ${index + 1}`;
-    microphoneSelect.appendChild(option);
-  });
-
-  const savedMicId = localStorage.getItem('selectedMicrophone');
-  if (savedMicId && availableMicrophones.some(mic => mic.deviceId === savedMicId)) {
-    microphoneSelect.value = savedMicId;
-    selectedMicrophoneId = savedMicId;
-  }
-}
-
-function handleMicrophoneChange() {
-  selectedMicrophoneId = microphoneSelect.value || null;
-  localStorage.setItem('selectedMicrophone', selectedMicrophoneId || '');
-
-  const selectedDevice = availableMicrophones.find(mic => mic.deviceId === selectedMicrophoneId);
-  const deviceName = selectedDevice ? selectedDevice.label : 'Default Microphone';
-
-  console.log(`Selected microphone: ${deviceName}`);
-  statusText.textContent = `Microphone changed to: ${deviceName}`;
-
-  if (isRecording) {
-    statusText.textContent = "Switching microphone... Please wait.";
-    stopRecording().then(() => {
-      setTimeout(() => {
-        toggleRecording();
-      }, 1000);
-    });
-  }
-}
-
-// Helpers
-function fmt1(x) {
-  const n = Number(x);
-  return Number.isFinite(n) ? n.toFixed(1) : x;
-}
-
-// Default WebSocket URL computation
-const host = window.location.hostname || "localhost";
-const port = window.location.port;
-const protocol = window.location.protocol === "https:" ? "wss" : "ws";
-const defaultWebSocketUrl = websocketUrl;
-
-// Populate default caption and input
-if (websocketDefaultSpan) websocketDefaultSpan.textContent = defaultWebSocketUrl;
-websocketInput.value = defaultWebSocketUrl;
-websocketUrl = defaultWebSocketUrl;
-
-// Optional chunk selector (guard for presence)
-if (chunkSelector) {
-  chunkSelector.addEventListener("change", () => {
-    chunkDuration = parseInt(chunkSelector.value);
-  });
-}
-
-// WebSocket input change handling
-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
-            );
-          }
-        }
-      } 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"));
-    };
-
-    websocket.onmessage = (event) => {
-      const data = JSON.parse(event.data);
-
-      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,
-            0,
-            true
-          );
-        }
-        statusText.textContent = "Finished processing audio! Ready to record again.";
-        recordButton.disabled = false;
-
-        if (websocket) {
-          websocket.close();
-        }
-        return;
-      }
-
-      lastReceivedData = data;
-
-      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: var(--muted); margin-top: 20px;'><em>No audio detected...</em></p>";
-    return;
-  }
-
-  const showLoading = !isFinalizing && (lines || []).some((it) => it.speaker == 0);
-  const showTransLag = !isFinalizing && remaining_time_transcription > 0;
-  const showDiaLag = !isFinalizing && !!buffer_diarization && remaining_time_diarization > 0;
-  const signature = JSON.stringify({
-    lines: (lines || []).map((it) => ({ speaker: it.speaker, text: it.text, start: it.start, end: it.end })),
-    buffer_transcription: buffer_transcription || "",
-    buffer_diarization: buffer_diarization || "",
-    status: current_status,
-    showLoading,
-    showTransLag,
-    showDiaLag,
-    isFinalizing: !!isFinalizing,
-  });
-  if (lastSignature === signature) {
-    const t = document.querySelector(".lag-transcription-value");
-    if (t) t.textContent = fmt1(remaining_time_transcription);
-    const d = document.querySelector(".lag-diarization-value");
-    if (d) d.textContent = fmt1(remaining_time_diarization);
-    const ld = document.querySelector(".loading-diarization-value");
-    if (ld) ld.textContent = fmt1(remaining_time_diarization);
-    return;
-  }
-  lastSignature = signature;
-
-  const linesHtml = (lines || [])
-    .map((item, idx) => {
-      let timeInfo = "";
-      if (item.start !== undefined && item.end !== undefined) {
-        timeInfo = ` ${item.start} - ${item.end}`;
-      }
-
-      let speakerLabel = "";
-      if (item.speaker === -2) {
-        speakerLabel = `<span class="silence">Silence<span id='timeInfo'>${timeInfo}</span></span>`;
-      } else if (item.speaker == 0 && !isFinalizing) {
-        speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'><span class="loading-diarization-value">${fmt1(
-          remaining_time_diarization
-        )}</span> second(s) of audio are undergoing diarization</span></span>`;
-      } else if (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 && item.speaker !== -2) {
-          if (remaining_time_transcription > 0) {
-            speakerLabel += `<span class="label_transcription"><span class="spinner"></span>Lag <span id='timeInfo'><span class="lag-transcription-value">${fmt1(
-              remaining_time_transcription
-            )}</span>s</span></span>`;
-          }
-          if (buffer_diarization && remaining_time_diarization > 0) {
-            speakerLabel += `<span class="label_diarization"><span class="spinner"></span>Lag<span id='timeInfo'><span class="lag-diarization-value">${fmt1(
-              remaining_time_diarization
-            )}</span>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>${speakerLabel}<br/></p>`;
-    })
-    .join("");
-
-  linesTranscriptDiv.innerHTML = linesHtml;
-  window.scrollTo({ top: document.body.scrollHeight, behavior: "smooth" });
-}
-
-function updateTimer() {
-  if (!startTime) return;
-
-  const elapsed = Math.floor((Date.now() - startTime) / 1000);
-  const minutes = Math.floor(elapsed / 60).toString().padStart(2, "0");
-  const seconds = (elapsed % 60).toString().padStart(2, "0");
-  timerElement.textContent = `${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 = waveStroke;
-  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 {
-    try {
-      wakeLock = await navigator.wakeLock.request("screen");
-    } catch (err) {
-      console.log("Error acquiring wake lock.");
-    }
-
-    let stream;
-    try {
-      // Try tab capture first
-      stream = await new Promise((resolve, reject) => {
-        chrome.tabCapture.capture({audio: true}, (s) => {
-          if (s) {
-            resolve(s);
-          } else {
-            reject(new Error('Tab capture failed or not available'));
-          }
-        });
-      });
-      statusText.textContent = "Using tab audio capture.";
-    } catch (tabError) {
-      console.log('Tab capture not available, falling back to microphone', tabError);
-      // Fallback to microphone
-      const audioConstraints = selectedMicrophoneId
-        ? { audio: { deviceId: { exact: selectedMicrophoneId } } }
-        : { audio: true };
-      stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
-      statusText.textContent = "Using microphone audio.";
-    }
-
-    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) {
-    if (window.location.hostname === "0.0.0.0") {
-      statusText.textContent =
-        "Error accessing audio input. Browsers may block audio access on 0.0.0.0. Try using localhost:8000 instead.";
-    } else {
-      statusText.textContent = "Error accessing audio input. Please check permissions.";
-    }
-    console.error(err);
-  }
-}
-
-async function stopRecording() {
-  if (wakeLock) {
-    try {
-      await wakeLock.release();
-    } catch (e) {
-      // ignore
-    }
-    wakeLock = null;
-  }
-
-  userClosing = true;
-  waitingForStop = true;
-
-  if (websocket && websocket.readyState === WebSocket.OPEN) {
-    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 {
-      await 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;
-    }
-    console.log("Connecting to WebSocket");
-    try {
-      if (websocket && websocket.readyState === WebSocket.OPEN) {
-        await startRecording();
-      } else {
-        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);
-
-if (microphoneSelect) {
-  microphoneSelect.addEventListener("change", handleMicrophoneChange);
-}
-
-// Settings toggle functionality
-settingsToggle.addEventListener("click", () => {
-  settingsDiv.classList.toggle("visible");
-  settingsToggle.classList.toggle("active");
-});
-
-document.addEventListener('DOMContentLoaded', async () => {
-  try {
-    await enumerateMicrophones();
-  } catch (error) {
-    console.log("Could not enumerate microphones on load:", error);
-  }
-});
-navigator.mediaDevices.addEventListener('devicechange', async () => {
-  console.log('Device change detected, re-enumerating microphones');
-  try {
-    await enumerateMicrophones();
-  } catch (error) {
-    console.log("Error re-enumerating microphones:", error);
-  }
-});
-
-
-async function run() {
-  const micPermission = await navigator.permissions.query({
-    name: "microphone",
-  });
-
-  document.getElementById(
-    "audioPermission"
-  ).innerText = `MICROPHONE: ${micPermission.state}`;
-
-  if (micPermission.state !== "granted") {
-    chrome.tabs.create({ url: "welcome.html" });
-  }
-
-  const intervalId = setInterval(async () => {
-    const micPermission = await navigator.permissions.query({
-      name: "microphone",
-    });
-    if (micPermission.state === "granted") {
-      document.getElementById(
-        "audioPermission"
-      ).innerText = `MICROPHONE: ${micPermission.state}`;
-      clearInterval(intervalId);
-    }
-  }, 100);
-}
-
-void run();

chrome-extension/manifest.json

@@ -3,9 +3,6 @@
     "name": "WhisperLiveKit Tab Capture",
     "version": "1.0",
     "description": "Capture and transcribe audio from browser tabs using WhisperLiveKit.",
-    "background": {
-        "service_worker": "background.js"
-    },
     "icons": {
         "16": "icons/icon16.png",
         "32": "icons/icon32.png",
@@ -14,7 +11,7 @@
     },
     "action": {
         "default_title": "WhisperLiveKit Tab Capture",
-        "default_popup": "popup.html"
+        "default_popup": "live_transcription.html"
     },
     "permissions": [
         "scripting",
@@ -22,16 +19,5 @@
         "offscreen",
         "activeTab",
         "storage"
-    ],
-    "web_accessible_resources": [
-        {
-            "resources": [
-                "requestPermissions.html",
-                "requestPermissions.js"
-            ],
-            "matches": [
-                "<all_urls>"
-            ]
-        }
     ]
 }

chrome-extension/popup.html

@@ -1,78 +0,0 @@
-<!DOCTYPE html>
-<html lang="en">
-
-<head>
-    <meta charset="UTF-8" />
-    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
-    <title>WhisperLiveKit</title>
-    <link rel="stylesheet" href="/web/live_transcription.css" />
-</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>
-
-        <button id="settingsToggle" class="settings-toggle" title="Show/hide settings">
-            <img src="/web/src/settings.svg" alt="Settings" />
-        </button>
-
-        <div class="settings">
-            <div class="field">
-                <label for="websocketInput">Websocket URL</label>
-                <input id="websocketInput" type="text" placeholder="ws://host:port/asr" />
-            </div>
-
-            <div class="field">
-                <label id="microphoneSelectLabel" for="microphoneSelect">Select Microphone</label>
-                <select id="microphoneSelect">
-                    <option value="">Default Microphone</option>
-                </select>
-                        <div id="audioPermission"></div>
-
-            </div>
-
-            <div class="theme-selector-container">
-                <div class="segmented" role="radiogroup" aria-label="Theme selector">
-                    <input type="radio" id="theme-system" name="theme" value="system" />
-                    <label for="theme-system" title="System">
-                        <img src="/web/src/system_mode.svg" alt="" />
-                        <!-- <span>System</span> -->
-                    </label>
-
-                    <input type="radio" id="theme-light" name="theme" value="light" />
-                    <label for="theme-light" title="Light">
-                        <img src="/web/src/light_mode.svg" alt="" />
-                        <!-- <span>Light</span> -->
-                    </label>
-
-                    <input type="radio" id="theme-dark" name="theme" value="dark" />
-                    <label for="theme-dark" title="Dark">
-                        <img src="/web/src/dark_mode.svg" alt="" />
-                        <!-- <span>Dark</span> -->
-                    </label>
-                </div>
-            </div>
-
-        </div>
-    </div>
-
-
-
-    <p id="status"></p>
-
-    <div id="linesTranscript"></div>
-
-    <script src="live_transcription.js"></script>
-</body>
-
-</html>

chrome-extension/web/live_transcription.css

@@ -1,539 +0,0 @@
-:root {
-  --bg: #ffffff;
-  --text: #111111;
-  --muted: #666666;
-  --border: #e5e5e5;
-  --chip-bg: rgba(0, 0, 0, 0.04);
-  --chip-text: #000000;
-  --spinner-border: #8d8d8d5c;
-  --spinner-top: #b0b0b0;
-  --silence-bg: #f3f3f3;
-  --loading-bg: rgba(255, 77, 77, 0.06);
-  --button-bg: #ffffff;
-  --button-border: #e9e9e9;
-  --wave-stroke: #000000;
-  --label-dia-text: #868686;
-  --label-trans-text: #111111;
-}
-
-@media (prefers-color-scheme: dark) {
-  :root:not([data-theme="light"]) {
-    --bg: #0b0b0b;
-    --text: #e6e6e6;
-    --muted: #9aa0a6;
-    --border: #333333;
-    --chip-bg: rgba(255, 255, 255, 0.08);
-    --chip-text: #e6e6e6;
-    --spinner-border: #555555;
-    --spinner-top: #dddddd;
-    --silence-bg: #1a1a1a;
-    --loading-bg: rgba(255, 77, 77, 0.12);
-    --button-bg: #111111;
-    --button-border: #333333;
-    --wave-stroke: #e6e6e6;
-    --label-dia-text: #b3b3b3;
-    --label-trans-text: #ffffff;
-  }
-}
-
-:root[data-theme="dark"] {
-  --bg: #0b0b0b;
-  --text: #e6e6e6;
-  --muted: #9aa0a6;
-  --border: #333333;
-  --chip-bg: rgba(255, 255, 255, 0.08);
-  --chip-text: #e6e6e6;
-  --spinner-border: #555555;
-  --spinner-top: #dddddd;
-  --silence-bg: #1a1a1a;
-  --loading-bg: rgba(255, 77, 77, 0.12);
-  --button-bg: #111111;
-  --button-border: #333333;
-  --wave-stroke: #e6e6e6;
-  --label-dia-text: #b3b3b3;
-  --label-trans-text: #ffffff;
-}
-
-:root[data-theme="light"] {
-  --bg: #ffffff;
-  --text: #111111;
-  --muted: #666666;
-  --border: #e5e5e5;
-  --chip-bg: rgba(0, 0, 0, 0.04);
-  --chip-text: #000000;
-  --spinner-border: #8d8d8d5c;
-  --spinner-top: #b0b0b0;
-  --silence-bg: #f3f3f3;
-  --loading-bg: rgba(255, 77, 77, 0.06);
-  --button-bg: #ffffff;
-  --button-border: #e9e9e9;
-  --wave-stroke: #000000;
-  --label-dia-text: #868686;
-  --label-trans-text: #111111;
-}
-
-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;
-  background-color: var(--bg);
-  color: var(--text);
-}
-
-.settings-toggle {
-  margin-top: 4px;
-  width: 40px;
-  height: 40px;
-  border: none;
-  border-radius: 50%;
-  background-color: var(--button-bg);
-  cursor: pointer;
-  transition: all 0.3s ease;
-  /* border: 1px solid var(--button-border); */
-  display: flex;
-  align-items: center;
-  justify-content: center;
-  position: relative;
-}
-
-.settings-toggle:hover {
-  background-color: var(--chip-bg);
-}
-
-.settings-toggle img {
-  width: 24px;
-  height: 24px;
-  opacity: 0.7;
-  transition: opacity 0.2s ease, transform 0.3s ease;
-}
-
-.settings-toggle:hover img {
-  opacity: 1;
-}
-
-.settings-toggle.active img {
-  transform: rotate(80deg);
-}
-
-/* Record button */
-#recordButton {
-  width: 50px;
-  height: 50px;
-  border: none;
-  border-radius: 50%;
-  background-color: var(--button-bg);
-  cursor: pointer;
-  transition: all 0.3s ease;
-  border: 1px solid var(--button-border);
-  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: var(--text);
-  margin-left: 10px;
-}
-
-#status {
-  margin-top: 20px;
-  font-size: 16px;
-  color: var(--text);
-}
-
-/* Settings */
-.settings-container {
-  display: flex;
-  justify-content: center;
-  align-items: flex-start;
-  gap: 15px;
-  margin-top: 20px;
-  flex-wrap: wrap;
-}
-
-.settings {
-  display: none;
-  flex-wrap: wrap;
-  align-items: flex-start;
-  gap: 12px;
-  transition: opacity 0.3s ease;
-}
-
-.settings.visible {
-  display: flex;
-}
-
-.field {
-  display: flex;
-  flex-direction: column;
-  align-items: flex-start;
-  gap: 3px;
-}
-
-#chunkSelector,
-#websocketInput,
-#themeSelector,
-#microphoneSelect {
-  font-size: 16px;
-  padding: 5px 8px;
-  border-radius: 8px;
-  border: 1px solid var(--border);
-  background-color: var(--button-bg);
-  color: var(--text);
-  max-height: 30px;
-}
-
-#microphoneSelect {
-  width: 100%;
-  max-width: 190px;
-  min-width: 120px;
-}
-
-#chunkSelector:focus,
-#websocketInput:focus,
-#themeSelector:focus,
-#microphoneSelect:focus {
-  outline: none;
-  border-color: #007bff;
-  box-shadow: 0 0 0 3px rgba(0, 123, 255, 0.15);
-}
-
-label {
-  font-size: 13px;
-  color: var(--muted);
-}
-
-.ws-default {
-  font-size: 12px;
-  color: var(--muted);
-}
-
-/* Segmented pill control for Theme */
-.segmented {
-  display: inline-flex;
-  align-items: stretch;
-  border: 1px solid var(--button-border);
-  background-color: var(--button-bg);
-  border-radius: 999px;
-  overflow: hidden;
-}
-
-.segmented input[type="radio"] {
-  position: absolute;
-  opacity: 0;
-  pointer-events: none;
-}
-
-.theme-selector-container {
-  display: flex;
-  align-items: center;
-  margin-top: 17px;
-}
-
-.segmented label {
-  display: inline-flex;
-  align-items: center;
-  gap: 6px;
-  padding: 6px 12px;
-  font-size: 14px;
-  color: var(--muted);
-  cursor: pointer;
-  user-select: none;
-  transition: background-color 0.2s ease, color 0.2s ease;
-}
-
-.segmented label span {
-  display: none;
-}
-
-.segmented label:hover span {
-  display: inline;
-}
-
-.segmented label:hover {
-  background-color: var(--chip-bg);
-}
-
-.segmented img {
-  width: 16px;
-  height: 16px;
-}
-
-.segmented input[type="radio"]:checked + label {
-  background-color: var(--chip-bg);
-  color: var(--text);
-}
-
-.segmented input[type="radio"]:focus-visible + label,
-.segmented input[type="radio"]:focus + label {
-  outline: 2px solid #007bff;
-  outline-offset: 2px;
-  border-radius: 999px;
-}
-
-/* Transcript area */
-#linesTranscript {
-  margin: 20px auto;
-  max-width: 700px;
-  text-align: left;
-  font-size: 16px;
-}
-
-#linesTranscript p {
-  margin: 0px 0;
-}
-
-#linesTranscript strong {
-  color: var(--text);
-}
-
-#speaker {
-  border: 1px solid var(--border);
-  border-radius: 100px;
-  padding: 2px 10px;
-  font-size: 14px;
-  margin-bottom: 0px;
-}
-
-.label_diarization {
-  background-color: var(--chip-bg);
-  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: var(--label-dia-text);
-}
-
-.label_transcription {
-  background-color: var(--chip-bg);
-  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: var(--label-trans-text);
-}
-
-#timeInfo {
-  color: var(--muted);
-  margin-left: 10px;
-}
-
-.textcontent {
-  font-size: 16px;
-  padding-left: 10px;
-  margin-bottom: 10px;
-  margin-top: 1px;
-  padding-top: 5px;
-  border-radius: 0px 0px 0px 10px;
-}
-
-.buffer_diarization {
-  color: var(--label-dia-text);
-  margin-left: 4px;
-}
-
-.buffer_transcription {
-  color: #7474748c;
-  margin-left: 4px;
-}
-
-.spinner {
-  display: inline-block;
-  width: 8px;
-  height: 8px;
-  border: 2px solid var(--spinner-border);
-  border-top: 2px solid var(--spinner-top);
-  border-radius: 50%;
-  animation: spin 0.7s linear infinite;
-  vertical-align: middle;
-  margin-bottom: 2px;
-  margin-right: 5px;
-}
-
-@keyframes spin {
-  to {
-    transform: rotate(360deg);
-  }
-}
-
-.silence {
-  color: var(--muted);
-  background-color: var(--silence-bg);
-  font-size: 13px;
-  border-radius: 30px;
-  padding: 2px 10px;
-}
-
-.loading {
-  color: var(--muted);
-  background-color: var(--loading-bg);
-  border-radius: 8px 8px 8px 0px;
-  padding: 2px 10px;
-  font-size: 14px;
-  margin-bottom: 0px;
-}
-
-/* for smaller screens */
-/* @media (max-width: 450px) {
-  .settings-container {
-    flex-direction: column;
-    gap: 10px;
-    align-items: center;
-  }
-
-  .settings {
-    justify-content: center;
-    gap: 8px;
-    width: 100%;
-  }
-
-  .field {
-    align-items: center;
-    width: 100%;
-  }
-
-  #websocketInput,
-  #microphoneSelect {
-    min-width: 200px;
-    max-width: 100%;
-  }
-
-  .theme-selector-container {
-    margin-top: 10px;
-  }
-} */
-
-/* @media (max-width: 768px) and (min-width: 451px) {
-  .settings-container {
-    gap: 10px;
-  }
-
-  .settings {
-    gap: 8px;
-  }
-
-  #websocketInput,
-  #microphoneSelect {
-    min-width: 150px;
-    max-width: 300px;
-  }
-} */
-
-/* @media (max-width: 480px) {
-  body {
-    margin: 10px;
-  }
-
-  .settings-toggle {
-    width: 35px;
-    height: 35px;
-  }
-
-  .settings-toggle img {
-    width: 20px;
-    height: 20px;
-  }
-
-  .settings {
-    flex-direction: column;
-    align-items: center;
-    gap: 6px;
-  }
-
-  #websocketInput,
-  #microphoneSelect {
-    max-width: 400px;
-  }
-
-  .segmented label {
-    padding: 4px 8px;
-    font-size: 12px;
-  }
-
-  .segmented img {
-    width: 14px;
-    height: 14px;
-  }
-} */
-
-
-html
-{
-    width: 400px;  /* max: 800px */
-    height: 600px; /* max: 600px */
-    border-radius: 10px;
-
-}

chrome-extension/web/src/dark_mode.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M480-120q-151 0-255.5-104.5T120-480q0-138 90-239.5T440-838q13-2 23 3.5t16 14.5q6 9 6.5 21t-7.5 23q-17 26-25.5 55t-8.5 61q0 90 63 153t153 63q31 0 61.5-9t54.5-25q11-7 22.5-6.5T819-479q10 5 15.5 15t3.5 24q-14 138-117.5 229T480-120Zm0-80q88 0 158-48.5T740-375q-20 5-40 8t-40 3q-123 0-209.5-86.5T364-660q0-20 3-40t8-40q-78 32-126.5 102T200-480q0 116 82 198t198 82Zm-10-270Z"/></svg>

chrome-extension/web/src/light_mode.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M480-360q50 0 85-35t35-85q0-50-35-85t-85-35q-50 0-85 35t-35 85q0 50 35 85t85 35Zm0 80q-83 0-141.5-58.5T280-480q0-83 58.5-141.5T480-680q83 0 141.5 58.5T680-480q0 83-58.5 141.5T480-280ZM80-440q-17 0-28.5-11.5T40-480q0-17 11.5-28.5T80-520h80q17 0 28.5 11.5T200-480q0 17-11.5 28.5T160-440H80Zm720 0q-17 0-28.5-11.5T760-480q0-17 11.5-28.5T800-520h80q17 0 28.5 11.5T920-480q0 17-11.5 28.5T880-440h-80ZM480-760q-17 0-28.5-11.5T440-800v-80q0-17 11.5-28.5T480-920q17 0 28.5 11.5T520-880v80q0 17-11.5 28.5T480-760Zm0 720q-17 0-28.5-11.5T440-80v-80q0-17 11.5-28.5T480-200q17 0 28.5 11.5T520-160v80q0 17-11.5 28.5T480-40ZM226-678l-43-42q-12-11-11.5-28t11.5-29q12-12 29-12t28 12l42 43q11 12 11 28t-11 28q-11 12-27.5 11.5T226-678Zm494 495-42-43q-11-12-11-28.5t11-27.5q11-12 27.5-11.5T734-282l43 42q12 11 11.5 28T777-183q-12 12-29 12t-28-12Zm-42-495q-12-11-11.5-27.5T678-734l42-43q11-12 28-11.5t29 11.5q12 12 12 29t-12 28l-43 42q-12 11-28 11t-28-11ZM183-183q-12-12-12-29t12-28l43-42q12-11 28.5-11t27.5 11q12 11 11.5 27.5T282-226l-42 43q-11 12-28 11.5T183-183Zm297-297Z"/></svg>

chrome-extension/web/src/settings.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M433-80q-27 0-46.5-18T363-142l-9-66q-13-5-24.5-12T307-235l-62 26q-25 11-50 2t-39-32l-47-82q-14-23-8-49t27-43l53-40q-1-7-1-13.5v-27q0-6.5 1-13.5l-53-40q-21-17-27-43t8-49l47-82q14-23 39-32t50 2l62 26q11-8 23-15t24-12l9-66q4-26 23.5-44t46.5-18h94q27 0 46.5 18t23.5 44l9 66q13 5 24.5 12t22.5 15l62-26q25-11 50-2t39 32l47 82q14 23 8 49t-27 43l-53 40q1 7 1 13.5v27q0 6.5-2 13.5l53 40q21 17 27 43t-8 49l-48 82q-14 23-39 32t-50-2l-60-26q-11 8-23 15t-24 12l-9 66q-4 26-23.5 44T527-80h-94Zm7-80h79l14-106q31-8 57.5-23.5T639-327l99 41 39-68-86-65q5-14 7-29.5t2-31.5q0-16-2-31.5t-7-29.5l86-65-39-68-99 42q-22-23-48.5-38.5T533-694l-13-106h-79l-14 106q-31 8-57.5 23.5T321-633l-99-41-39 68 86 64q-5 15-7 30t-2 32q0 16 2 31t7 30l-86 65 39 68 99-42q22 23 48.5 38.5T427-266l13 106Zm42-180q58 0 99-41t41-99q0-58-41-99t-99-41q-59 0-99.5 41T342-480q0 58 40.5 99t99.5 41Zm-2-140Z"/></svg>

chrome-extension/web/src/system_mode.svg

@@ -1 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" height="24px" viewBox="0 -960 960 960" width="24px" fill="#5f6368"><path d="M396-396q-32-32-58.5-67T289-537q-5 14-6.5 28.5T281-480q0 83 58 141t141 58q14 0 28.5-2t28.5-6q-39-22-74-48.5T396-396Zm85 196q-56 0-107-21t-91-61q-40-40-61-91t-21-107q0-51 17-97.5t50-84.5q13-14 32-9.5t27 24.5q21 55 52.5 104t73.5 91q42 42 91 73.5T648-326q20 8 24.5 27t-9.5 32q-38 33-84.5 50T481-200Zm223-192q-16-5-23-20.5t-4-32.5q9-48-6-94.5T621-621q-35-35-80.5-49.5T448-677q-17 3-32-4t-21-23q-6-16 1.5-31t23.5-19q69-15 138 4.5T679-678q51 51 71 120t5 138q-4 17-19 25t-32 3ZM480-840q-17 0-28.5-11.5T440-880v-40q0-17 11.5-28.5T480-960q17 0 28.5 11.5T520-920v40q0 17-11.5 28.5T480-840Zm0 840q-17 0-28.5-11.5T440-40v-40q0-17 11.5-28.5T480-120q17 0 28.5 11.5T520-80v40q0 17-11.5 28.5T480 0Zm255-734q-12-12-12-28.5t12-28.5l28-28q11-11 27.5-11t28.5 11q12 12 12 28.5T819-762l-28 28q-12 12-28 12t-28-12ZM141-141q-12-12-12-28.5t12-28.5l28-28q12-12 28-12t28 12q12 12 12 28.5T225-169l-28 28q-11 11-27.5 11T141-141Zm739-299q-17 0-28.5-11.5T840-480q0-17 11.5-28.5T880-520h40q17 0 28.5 11.5T960-480q0 17-11.5 28.5T920-440h-40Zm-840 0q-17 0-28.5-11.5T0-480q0-17 11.5-28.5T40-520h40q17 0 28.5 11.5T120-480q0 17-11.5 28.5T80-440H40Zm779 299q-12 12-28.5 12T762-141l-28-28q-12-12-12-28t12-28q12-12 28.5-12t28.5 12l28 28q11 11 11 27.5T819-141ZM226-735q-12 12-28.5 12T169-735l-28-28q-11-11-11-27.5t11-28.5q12-12 28.5-12t28.5 12l28 28q12 12 12 28t-12 28Zm170 339Z"/></svg>

chrome-extension/welcome.html

@@ -1,12 +0,0 @@
-<!DOCTYPE html>
-<html>
-  <head>
-    <title>Welcome</title>
-    <script src="welcome.js"></script>
-  </head>
-  <body>
-    This page exists to workaround an issue with Chrome that blocks permission
-    requests from chrome extensions
-    <!-- <button id="requestMicrophone">Request Microphone</button> -->
-  </body>
-</html>

docs/API.md

@@ -0,0 +1,264 @@
+# WhisperLiveKit WebSocket API Documentation
+
+> !! **Note**: The new API structure described in this document is currently under deployment. 
+This documentation is intended for devs who want to build custom frontends.
+
+WLK provides real-time speech transcription, speaker diarization, and translation through a WebSocket API. The server sends incremental updates as audio is processed, allowing clients to display live transcription results with minimal latency.
+
+---
+
+## Legacy API (Current)
+
+### Message Structure
+
+The current API sends complete state snapshots on each update (several time per second)
+
+```typescript
+{
+  "type": str,
+  "status": str,
+  "lines": [
+    {
+      "speaker": int,
+      "text": str,
+      "start": float,
+      "end": float,
+      "translation": str | null,
+      "detected_language": str
+    }
+  ],
+  "buffer_transcription": str,
+  "buffer_diarization": str,
+  "remaining_time_transcription": float,
+  "remaining_time_diarization": float
+}
+```
+
+---
+
+## New API (Under Development)
+
+### Philosophy
+
+Principles:
+
+- **Incremental Updates**: Only updates and new segments are sent
+- **Ephemeral Buffers**: Temporary, unvalidated data displayed in real-time but overwritten on next update, at speaker level
+
+
+## Message Format
+
+
+```typescript
+{
+  "type": "transcript_update",
+  "status": "active_transcription" | "no_audio_detected",
+  "segments": [
+    {
+      "id": number,
+      "speaker": number,
+      "text": string,
+      "start_speaker": float,
+      "start": float,
+      "end": float,
+      "language": string | null,
+      "translation": string,
+      "words": [
+        {
+          "text": string,
+          "start": float,
+          "end": float,
+          "validated": {
+            "text": boolean,
+            "speaker": boolean,
+          }
+        }
+      ],
+      "buffer": {
+        "transcription": string,
+        "diarization": string,
+        "translation": string
+      }
+    }
+  ],
+  "metadata": {
+    "remaining_time_transcription": float,
+    "remaining_time_diarization": float
+  }
+}
+```
+
+### Other Message Types
+
+#### Config Message (sent on connection)
+```json
+{
+  "type": "config",
+  "useAudioWorklet": true / false
+}
+```
+
+#### Ready to Stop Message (sent after processing complete)
+```json
+{
+  "type": "ready_to_stop"
+}
+```
+
+---
+
+## Field Descriptions
+
+### Segment Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `id` | `number` | Unique identifier for this segment. Used by clients to update specific segments efficiently. |
+| `speaker` | `number` | Speaker ID (1, 2, 3...). Special value `-2` indicates silence. |
+| `text` | `string` | Validated transcription text for this update. Should be **appended** to the segment's text on the client side.  |
+| `start_speaker` | `float` | Timestamp (seconds) when this speaker segment began. |
+| `start` | `float` | Timestamp (seconds) of the first word in this update. |
+| `end` | `float` | Timestamp (seconds) of the last word in this update. |
+| `language` | `string \| null` | ISO language code (e.g., "en", "fr"). `null` until language is detected. |
+| `translation` | `string` | Validated translation text for this update. Should be **appended** to the segment's translation on the client side. |
+| `words` | `Array` | Array of word-level objects with timing and validation information. |
+| `buffer` | `Object` | Per-segment temporary buffers, see below |
+
+### Word Object
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `text` | `string` | The word text. |
+| `start` | `number` | Start timestamp (seconds) of this word. |
+| `end` | `number` | End timestamp (seconds) of this word. |
+| `validated.text` | `boolean` | Whether the transcription text has been validated. if false, word is also in buffer: transcription |
+| `validated.speaker` | `boolean` | Whether the speaker assignment has been validated. if false, word is also in buffer: diarization |
+| `validated.language` | `boolean` | Whether the language detection has been validated. if false, word is also in buffer: translation |
+
+### Buffer Object (Per-Segment)
+
+Buffers are **ephemeral**. They should be displayed to the user but not stored permanently in the frontend. Each update may contain a completely different buffer value, and previous buffer is likely to be in the next validated text.
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `transcription` | `string` | Pending transcription text. Displayed immediately but **overwritten** on next update. |
+| `diarization` | `string` | Pending diarization text (text waiting for speaker assignment). Displayed immediately but **overwritten** on next update. |
+| `translation` | `string` | Pending translation text. Displayed immediately but **overwritten** on next update. |
+
+
+### Metadata Fields
+
+| Field | Type | Description |
+|-------|------|-------------|
+| `remaining_time_transcription` | `float` | Seconds of audio waiting for transcription processing. |
+| `remaining_time_diarization` | `float` | Seconds of audio waiting for speaker diarization. |
+
+### Status Values
+
+| Status | Description |
+|--------|-------------|
+| `active_transcription` | Normal operation, transcription is active. |
+| `no_audio_detected` | No audio has been detected yet. |
+
+---
+
+## Update Behavior
+
+### Incremental Updates
+
+The API sends **only changed or new segments**. Clients should:
+
+1. Maintain a local map of segments by ID
+2. When receiving an update, merge/update segments by ID
+3. Render only the changed segments
+
+### Language Detection
+
+When language is detected for a segment:
+
+```jsonc
+// Update 1: No language yet
+{
+  "segments": [
+    {"id": 1, "speaker": 1, "text": "May see", "language": null}
+  ]
+}
+
+// Update 2: Same segment ID, language now detected
+{
+  "segments": [
+    {"id": 1, "speaker": 1, "text": "Merci", "language": "fr"}
+  ]
+}
+```
+
+**Client behavior**: **Replace** the existing segment with the same ID.
+
+### Buffer Behavior
+
+Buffers are **per-segment** to handle multi-speaker scenarios correctly.
+
+#### Example: Translation with diarization and translation
+
+```jsonc
+// Update 1
+{
+  "segments": [
+    {
+      "id": 1,
+      "speaker": 1,
+      "text": "Hello world, how are",
+      "translation": "",
+      "buffer": {
+        "transcription": "",
+        "diarization": " you on",
+        "translation": "Bonjour le monde"
+      }
+    }
+  ]
+}
+
+
+// ==== Frontend ====
+// <SPEAKER>1</SPEAKER>
+// <TRANSCRIPTION>Hello world, how are <DIARIZATION BUFFER> you on</DIARIZATION BUFFER></TRANSCRIPTION>
+// <TRANSLATION><TRANSLATION BUFFER>Bonjour le monde</TRANSLATION BUFFER></TRANSLATION>
+
+
+// Update 2
+{
+  "segments": [
+    {
+      "id": 1,
+      "speaker": 1,
+      "text": " you on this",
+      "translation": "Bonjour tout le monde",
+      "buffer": {
+        "transcription": "",
+        "diarization": " beautiful day",
+        "translation": ",comment"
+      }
+    },
+  ]
+}
+
+
+// ==== Frontend ====
+// <SPEAKER>1</SPEAKER>
+// <TRANSCRIPTION>Hello world, how are you on this<DIARIZATION BUFFER>  beautiful day</DIARIZATION BUFFER></TRANSCRIPTION>
+// <TRANSLATION>Bonjour tout le monde<TRANSLATION BUFFER>, comment</TRANSLATION BUFFER><TRANSLATION>
+```
+
+### Silence Segments
+
+Silence is represented with the speaker id = `-2`:
+
+```jsonc
+{
+  "id": 5,
+  "speaker": -2,
+  "text": "",
+  "start": 10.5,
+  "end": 12.3
+}
+```

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "whisperlivekit"
-version = "0.2.10"
+version = "0.2.12"
 description = "Real-time speech-to-text with speaker diarization using Whisper"
 readme = "README.md"
 authors = [
@@ -50,7 +50,7 @@ Homepage = "https://github.com/QuentinFuxa/WhisperLiveKit"
 whisperlivekit-server = "whisperlivekit.basic_server:main"
 
 [tool.setuptools]
-packages = ["whisperlivekit", "whisperlivekit.diarization", "whisperlivekit.simul_whisper", "whisperlivekit.simul_whisper.whisper", "whisperlivekit.simul_whisper.whisper.assets", "whisperlivekit.simul_whisper.whisper.normalizers", "whisperlivekit.web", "whisperlivekit.whisper_streaming_custom"]
+packages = ["whisperlivekit", "whisperlivekit.diarization", "whisperlivekit.simul_whisper", "whisperlivekit.simul_whisper.whisper", "whisperlivekit.simul_whisper.whisper.assets", "whisperlivekit.simul_whisper.whisper.normalizers", "whisperlivekit.web", "whisperlivekit.whisper_streaming_custom", "whisperlivekit.translation"]
 
 [tool.setuptools.package-data]
 whisperlivekit = ["web/*.html", "web/*.css", "web/*.js", "web/src/*.svg"]

sync_extension.py

@@ -0,0 +1,38 @@
+import shutil
+import os
+from pathlib import Path
+
+def sync_extension_files():
+    """Copy core files from web directory to Chrome extension directory."""
+    
+    web_dir = Path("whisperlivekit/web")
+    extension_dir = Path("chrome-extension")
+    
+    files_to_sync = [
+        "live_transcription.html", "live_transcription.js", "live_transcription.css"
+    ]
+
+    svg_files = [
+        "system_mode.svg",
+        "light_mode.svg", 
+        "dark_mode.svg",
+        "settings.svg"
+    ]
+        
+    for file in files_to_sync:
+        src_path = web_dir / file
+        dest_path = extension_dir / file
+        
+        dest_path.parent.mkdir(parents=True, exist_ok=True)
+        shutil.copy2(src_path, dest_path)
+    
+    for svg_file in svg_files:
+        src_path = web_dir / "src" / svg_file
+        dest_path = extension_dir / "web" / "src" / svg_file
+        dest_path.parent.mkdir(parents=True, exist_ok=True)
+        shutil.copy2(src_path, dest_path)
+    
+
+if __name__ == "__main__":
+
+    sync_extension_files()

whisperlivekit/audio_processor.py

@@ -4,18 +4,30 @@ from time import time, sleep
 import math
 import logging
 import traceback
-from whisperlivekit.timed_objects import ASRToken, Silence, Line, FrontData, State, Transcript
+from whisperlivekit.timed_objects import ASRToken, Silence, Line, FrontData, State, Transcript, ChangeSpeaker
 from whisperlivekit.core import TranscriptionEngine, online_factory, online_diarization_factory, online_translation_factory
 from whisperlivekit.silero_vad_iterator import FixedVADIterator
 from whisperlivekit.results_formater import format_output
 from whisperlivekit.ffmpeg_manager import FFmpegManager, FFmpegState
-# Set up logging once
+
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
 
 SENTINEL = object() # unique sentinel object for end of stream marker
 
+def cut_at(cumulative_pcm, cut_sec):
+    cumulative_len = 0
+    cut_sample = int(cut_sec * 16000)
+    
+    for ind, pcm_array in enumerate(cumulative_pcm):
+        if (cumulative_len + len(pcm_array)) >= cut_sample:
+            cut_chunk = cut_sample - cumulative_len
+            before = np.concatenate(cumulative_pcm[:ind] + [cumulative_pcm[ind][:cut_chunk]])
+            after = [cumulative_pcm[ind][cut_chunk:]] + cumulative_pcm[ind+1:]
+            return before, after
+        cumulative_len += len(pcm_array)
+    return np.concatenate(cumulative_pcm), []
 
 async def get_all_from_queue(queue):
     items = []
@@ -50,28 +62,32 @@ class AudioProcessor:
         self.bytes_per_sec = self.samples_per_sec * self.bytes_per_sample
         self.max_bytes_per_sec = 32000 * 5  # 5 seconds of audio at 32 kHz
         self.is_pcm_input = self.args.pcm_input
-        self.debug = False
 
         # State management
         self.is_stopping = False
         self.silence = False
         self.silence_duration = 0.0
         self.tokens = []
+        self.last_validated_token = 0
         self.translated_segments = []
         self.buffer_transcription = Transcript()
-        self.buffer_diarization = ""
         self.end_buffer = 0
         self.end_attributed_speaker = 0
         self.lock = asyncio.Lock()
-        self.beg_loop = None #to deal with a potential little lag at the websocket initialization, this is now set in process_audio
+        self.beg_loop = 0.0 #to deal with a potential little lag at the websocket initialization, this is now set in process_audio
         self.sep = " "  # Default separator
         self.last_response_content = FrontData()
         self.last_detected_speaker = None
         self.speaker_languages = {}
+        self.diarization_before_transcription = False
+
+        if self.diarization_before_transcription:
+            self.cumulative_pcm = []
+            self.last_start = 0.0
+            self.last_end = 0.0
         
         # Models and processing
         self.asr = models.asr
-        self.tokenizer = models.tokenizer
         self.vac_model = models.vac_model
         if self.args.vac:
             self.vac = FixedVADIterator(models.vac_model)
@@ -99,16 +115,21 @@ class AudioProcessor:
 
         self.transcription_task = None
         self.diarization_task = None
+        self.translation_task = None
         self.watchdog_task = None
         self.all_tasks_for_cleanup = []
         
+        self.transcription = None
+        self.translation = None
+        self.diarization = None
+
         if self.args.transcription:
-            self.online = online_factory(self.args, models.asr, models.tokenizer)        
+            self.transcription = online_factory(self.args, models.asr)        
-            self.sep = self.online.asr.sep   
+            self.sep = self.transcription.asr.sep   
         if self.args.diarization:
             self.diarization = online_diarization_factory(self.args, models.diarization_model)
-        if self.args.target_language:
+        if models.translation_model:
-            self.online_translation = online_translation_factory(self.args, models.translation_model)
+            self.translation = online_translation_factory(self.args, models.translation_model)
 
     def convert_pcm_to_float(self, pcm_buffer):
         """Convert PCM buffer in s16le format to normalized NumPy array."""
@@ -117,7 +138,7 @@ class AudioProcessor:
     async def add_dummy_token(self):
         """Placeholder token when no transcription is available."""
         async with self.lock:
-            current_time = time() - self.beg_loop if self.beg_loop else 0
+            current_time = time() - self.beg_loop
             self.tokens.append(ASRToken(
                 start=current_time, end=current_time + 1,
                 text=".", speaker=-1, is_dummy=True
@@ -140,9 +161,9 @@ class AudioProcessor:
                 
             return State(
                 tokens=self.tokens.copy(),
+                last_validated_token=self.last_validated_token,
                 translated_segments=self.translated_segments.copy(),
                 buffer_transcription=self.buffer_transcription,
-                buffer_diarization=self.buffer_diarization,
                 end_buffer=self.end_buffer,
                 end_attributed_speaker=self.end_attributed_speaker,
                 remaining_time_transcription=remaining_transcription,
@@ -154,7 +175,7 @@ class AudioProcessor:
         async with self.lock:
             self.tokens = []
             self.translated_segments = []
-            self.buffer_transcription = self.buffer_diarization = Transcript()
+            self.buffer_transcription = Transcript()
             self.end_buffer = self.end_attributed_speaker = 0
             self.beg_loop = time()
 
@@ -201,11 +222,11 @@ class AudioProcessor:
                 await asyncio.sleep(0.2)
 
         logger.info("FFmpeg stdout processing finished. Signaling downstream processors if needed.")
-        if self.args.transcription and self.transcription_queue:
+        if not self.diarization_before_transcription and self.transcription_queue:
             await self.transcription_queue.put(SENTINEL)
-        if self.args.diarization and self.diarization_queue:
+        if self.diarization:
             await self.diarization_queue.put(SENTINEL)
-        if self.args.target_language and self.translation_queue:
+        if self.translation:
             await self.translation_queue.put(SENTINEL)
 
     async def transcription_processor(self):
@@ -219,13 +240,8 @@ class AudioProcessor:
                     logger.debug("Transcription processor received sentinel. Finishing.")
                     self.transcription_queue.task_done()
                     break
-                
-                if not self.online:
-                    logger.warning("Transcription processor: self.online not initialized.")
-                    self.transcription_queue.task_done()
-                    continue
 
-                asr_internal_buffer_duration_s = len(getattr(self.online, 'audio_buffer', [])) / self.online.SAMPLING_RATE
+                asr_internal_buffer_duration_s = len(getattr(self.transcription, 'audio_buffer', [])) / self.transcription.SAMPLING_RATE
                 transcription_lag_s = max(0.0, time() - self.beg_loop - self.end_buffer)
                 asr_processing_logs = f"internal_buffer={asr_internal_buffer_duration_s:.2f}s | lag={transcription_lag_s:.2f}s |"
                 if type(item) is Silence:
@@ -234,23 +250,23 @@ class AudioProcessor:
                         asr_processing_logs += f" | last_end = {self.tokens[-1].end} |"
                     logger.info(asr_processing_logs)
                     cumulative_pcm_duration_stream_time += item.duration
-                    self.online.insert_silence(item.duration, self.tokens[-1].end if self.tokens else 0)
+                    self.transcription.insert_silence(item.duration, self.tokens[-1].end if self.tokens else 0)
                     continue
-                logger.info(asr_processing_logs)
+                elif isinstance(item, ChangeSpeaker):
-                
+                    self.transcription.new_speaker(item)
-                if isinstance(item, np.ndarray):
+                elif isinstance(item, np.ndarray):
                     pcm_array = item
-                else:
+                
-                    raise Exception('item should be pcm_array')
+                logger.info(asr_processing_logs)
                 
                 duration_this_chunk = len(pcm_array) / self.sample_rate
                 cumulative_pcm_duration_stream_time += duration_this_chunk
                 stream_time_end_of_current_pcm = cumulative_pcm_duration_stream_time
 
-                self.online.insert_audio_chunk(pcm_array, stream_time_end_of_current_pcm)
+                self.transcription.insert_audio_chunk(pcm_array, stream_time_end_of_current_pcm)
-                new_tokens, current_audio_processed_upto = await asyncio.to_thread(self.online.process_iter)
+                new_tokens, current_audio_processed_upto = await asyncio.to_thread(self.transcription.process_iter)
                 
-                _buffer_transcript = self.online.get_buffer()
+                _buffer_transcript = self.transcription.get_buffer()
                 buffer_text = _buffer_transcript.text
 
                 if new_tokens:
@@ -297,8 +313,9 @@ class AudioProcessor:
 
     async def diarization_processor(self, diarization_obj):
         """Process audio chunks for speaker diarization."""
-        buffer_diarization = ""
+        if self.diarization_before_transcription:
-        cumulative_pcm_duration_stream_time = 0.0
+            self.current_speaker = 0
+            await self.transcription_queue.put(ChangeSpeaker(speaker=self.current_speaker, start=0.0))
         while True:
             try:
                 item = await self.diarization_queue.get()
@@ -307,7 +324,6 @@ class AudioProcessor:
                     self.diarization_queue.task_done()
                     break
                 elif type(item) is Silence:
-                    cumulative_pcm_duration_stream_time += item.duration
                     diarization_obj.insert_silence(item.duration)
                     continue
                 elif isinstance(item, np.ndarray):
@@ -315,24 +331,41 @@ class AudioProcessor:
                 else:
                     raise Exception('item should be pcm_array') 
                 
+                
+                
                 # Process diarization
                 await diarization_obj.diarize(pcm_array)
-                
+                if self.diarization_before_transcription:
-                async with self.lock:
+                    segments = diarization_obj.get_segments()
-                    self.tokens, last_segment = diarization_obj.assign_speakers_to_tokens(
+                    self.cumulative_pcm.append(pcm_array)
-                        self.tokens,
+                    if segments:
-                        use_punctuation_split=self.args.punctuation_split
+                        last_segment = segments[-1]                    
-                    )
+                        if last_segment.speaker != self.current_speaker:
-                    if len(self.tokens) > 0:
+                            cut_sec = last_segment.start - self.last_end
-                        self.end_attributed_speaker = max(self.tokens[-1].end, self.end_attributed_speaker)
+                            to_transcript, self.cumulative_pcm = cut_at(self.cumulative_pcm, cut_sec)
-                    if buffer_diarization:
+                            await self.transcription_queue.put(to_transcript)
-                        self.buffer_diarization = buffer_diarization
+                            
-
+                            self.current_speaker = last_segment.speaker
-                    # if last_segment is not None and last_segment.speaker != self.last_detected_speaker:
+                            await self.transcription_queue.put(ChangeSpeaker(speaker=self.current_speaker, start=last_segment.start))
-                    #     if not self.speaker_languages.get(last_segment.speaker, None):
+                            
-                    #         self.last_detected_speaker = last_segment.speaker
+                            cut_sec = last_segment.end - last_segment.start
-                    #         self.online.on_new_speaker(last_segment)
+                            to_transcript, self.cumulative_pcm = cut_at(self.cumulative_pcm, cut_sec)
-       
+                            await self.transcription_queue.put(to_transcript)                            
+                            self.last_start = last_segment.start
+                            self.last_end = last_segment.end
+                        else:
+                            cut_sec = last_segment.end - self.last_end
+                            to_transcript, self.cumulative_pcm = cut_at(self.cumulative_pcm, cut_sec)
+                            await self.transcription_queue.put(to_transcript)
+                            self.last_end = last_segment.end
+                elif not self.diarization_before_transcription:           
+                    async with self.lock:
+                        self.tokens = diarization_obj.assign_speakers_to_tokens(
+                            self.tokens,
+                            use_punctuation_split=self.args.punctuation_split
+                        )
+                if len(self.tokens) > 0:
+                    self.end_attributed_speaker = max(self.tokens[-1].end, self.end_attributed_speaker)
                 self.diarization_queue.task_done()
                 
             except Exception as e:
@@ -342,7 +375,7 @@ class AudioProcessor:
                     self.diarization_queue.task_done()
         logger.info("Diarization processor task finished.")
 
-    async def translation_processor(self, online_translation):
+    async def translation_processor(self):
         # the idea is to ignore diarization for the moment. We use only transcription tokens. 
         # And the speaker is attributed given the segments used for the translation
         # in the future we want to have different languages for each speaker etc, so it will be more complex.
@@ -354,7 +387,7 @@ class AudioProcessor:
                     self.translation_queue.task_done()
                     break
                 elif type(item) is Silence:
-                    online_translation.insert_silence(item.duration)
+                    self.translation.insert_silence(item.duration)
                     continue
                 
                 # get all the available tokens for translation. The more words, the more precise
@@ -366,11 +399,14 @@ class AudioProcessor:
                     if additional_token is SENTINEL:
                         sentinel_found = True
                         break
-                    tokens_to_process.append(additional_token)                
+                    elif type(additional_token) is Silence:
+                        self.translation.insert_silence(additional_token.duration)
+                        continue
+                    else:
+                        tokens_to_process.append(additional_token)                
                 if tokens_to_process:
-                    online_translation.insert_tokens(tokens_to_process)
+                    self.translation.insert_tokens(tokens_to_process)
-                    self.translated_segments = await asyncio.to_thread(online_translation.process)
+                    self.translated_segments = await asyncio.to_thread(self.translation.process)
-                
                 self.translation_queue.task_done()
                 for _ in additional_tokens:
                     self.translation_queue.task_done()
@@ -393,53 +429,33 @@ class AudioProcessor:
         """Format processing results for output."""
         while True:
             try:
-                # If FFmpeg error occurred, notify front-end
                 if self._ffmpeg_error:
-                    yield FrontData(
+                    yield FrontData(status="error", error=f"FFmpeg error: {self._ffmpeg_error}")
-                        status="error",
-                        error=f"FFmpeg error: {self._ffmpeg_error}"
-                    )
                     self._ffmpeg_error = None
                     await asyncio.sleep(1)
                     continue
 
-                # Get current state
                 state = await self.get_current_state()
-                                
-                # Add dummy tokens if needed
-                if (not state.tokens or state.tokens[-1].is_dummy) and not self.args.transcription and self.args.diarization:
-                    await self.add_dummy_token()
-                    sleep(0.5)
-                    state = await self.get_current_state()
                 
-                # Format output
+                
-                lines, undiarized_text, end_w_silence = format_output(
+                lines, undiarized_text = format_output(
                     state,
                     self.silence,
-                    current_time = time() - self.beg_loop if self.beg_loop else None,
+                    current_time = time() - self.beg_loop,
                     args = self.args,
-                    debug = self.debug,
                     sep=self.sep
                 )
-                if end_w_silence:
+                if lines and lines[-1].speaker == -2:
                     buffer_transcription = Transcript()
-                    buffer_diarization = Transcript()
                 else:
                     buffer_transcription = state.buffer_transcription
-                    buffer_diarization = state.buffer_diarization
 
-                # Handle undiarized text
+                buffer_diarization = ''
                 if undiarized_text:
-                    combined = self.sep.join(undiarized_text)
+                    buffer_diarization = self.sep.join(undiarized_text)
-                    if buffer_transcription:
-                        combined += self.sep
 
                     async with self.lock:
                         self.end_attributed_speaker = state.end_attributed_speaker
-                        if buffer_diarization:
-                            self.buffer_diarization = buffer_diarization
-
-                    buffer_diarization.text = combined
                 
                 response_status = "active_transcription"
                 if not state.tokens and not buffer_transcription and not buffer_diarization:
@@ -455,8 +471,8 @@ class AudioProcessor:
                 response = FrontData(
                     status=response_status,
                     lines=lines,
-                    buffer_transcription=buffer_transcription.text,
+                    buffer_transcription=buffer_transcription.text.strip(),
-                    buffer_diarization=buffer_transcription.text,
+                    buffer_diarization=buffer_diarization,
                     remaining_time_transcription=state.remaining_time_transcription,
                     remaining_time_diarization=state.remaining_time_diarization if self.args.diarization else 0
                 )
@@ -505,18 +521,18 @@ class AudioProcessor:
             self.all_tasks_for_cleanup.append(self.ffmpeg_reader_task)
             processing_tasks_for_watchdog.append(self.ffmpeg_reader_task)
 
-        if self.args.transcription and self.online:
+        if self.transcription:
             self.transcription_task = asyncio.create_task(self.transcription_processor())
             self.all_tasks_for_cleanup.append(self.transcription_task)
             processing_tasks_for_watchdog.append(self.transcription_task)
             
-        if self.args.diarization and self.diarization:
+        if self.diarization:
             self.diarization_task = asyncio.create_task(self.diarization_processor(self.diarization))
             self.all_tasks_for_cleanup.append(self.diarization_task)
             processing_tasks_for_watchdog.append(self.diarization_task)
         
-        if self.args.target_language and self.args.lan != 'auto':
+        if self.translation:
-            self.translation_task = asyncio.create_task(self.translation_processor(self.online_translation))
+            self.translation_task = asyncio.create_task(self.translation_processor())
             self.all_tasks_for_cleanup.append(self.translation_task)
             processing_tasks_for_watchdog.append(self.translation_task)
         
@@ -566,7 +582,7 @@ class AudioProcessor:
                 logger.info("FFmpeg manager stopped.")
             except Exception as e:
                 logger.warning(f"Error stopping FFmpeg manager: {e}")
-        if self.args.diarization and hasattr(self, 'dianization') and hasattr(self.diarization, 'close'):
+        if self.diarization:
             self.diarization.close()
         logger.info("AudioProcessor cleanup complete.")
 
@@ -619,9 +635,13 @@ class AudioProcessor:
                 f"Consider using a smaller model."
             )
 
-        # Process audio chunk
+        chunk_size = min(len(self.pcm_buffer), self.max_bytes_per_sec)
-        pcm_array = self.convert_pcm_to_float(self.pcm_buffer[:self.max_bytes_per_sec])
+        aligned_chunk_size = (chunk_size // self.bytes_per_sample) * self.bytes_per_sample
-        self.pcm_buffer = self.pcm_buffer[self.max_bytes_per_sec:]
+        
+        if aligned_chunk_size == 0:
+            return
+        pcm_array = self.convert_pcm_to_float(self.pcm_buffer[:aligned_chunk_size])
+        self.pcm_buffer = self.pcm_buffer[aligned_chunk_size:]
 
         res = None
         end_of_audio = False
@@ -638,7 +658,7 @@ class AudioProcessor:
                 silence_buffer = Silence(duration=time() - self.start_silence)
 
         if silence_buffer:
-            if self.args.transcription and self.transcription_queue:
+            if not self.diarization_before_transcription and self.transcription_queue:
                 await self.transcription_queue.put(silence_buffer)
             if self.args.diarization and self.diarization_queue:
                 await self.diarization_queue.put(silence_buffer)
@@ -646,7 +666,7 @@ class AudioProcessor:
                 await self.translation_queue.put(silence_buffer)
 
         if not self.silence:
-            if self.args.transcription and self.transcription_queue:
+            if not self.diarization_before_transcription and self.transcription_queue:
                 await self.transcription_queue.put(pcm_array.copy())
 
             if self.args.diarization and self.diarization_queue:

whisperlivekit/basic_server.py

@@ -5,9 +5,6 @@ from fastapi.middleware.cors import CORSMiddleware
 from whisperlivekit import TranscriptionEngine, AudioProcessor, get_inline_ui_html, parse_args
 import asyncio
 import logging
-from starlette.staticfiles import StaticFiles
-import pathlib
-import whisperlivekit.web as webpkg
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")
 logging.getLogger().setLevel(logging.WARNING)
@@ -33,8 +30,6 @@ app.add_middleware(
     allow_methods=["*"],
     allow_headers=["*"],
 )
-web_dir = pathlib.Path(webpkg.__file__).parent
-app.mount("/web", StaticFiles(directory=str(web_dir)), name="web")
 
 @app.get("/")
 async def get():
@@ -123,6 +118,8 @@ def main():
 
     if ssl_kwargs:
         uvicorn_kwargs = {**uvicorn_kwargs, **ssl_kwargs}
+    if args.forwarded_allow_ips:
+        uvicorn_kwargs = { **uvicorn_kwargs, "forwarded_allow_ips" : args.forwarded_allow_ips }
 
     uvicorn.run(**uvicorn_kwargs)
 

whisperlivekit/core.py

@@ -4,10 +4,15 @@ try:
 except ImportError:
     from .whisper_streaming_custom.whisper_online import backend_factory
     from .whisper_streaming_custom.online_asr import OnlineASRProcessor
-from whisperlivekit.warmup import warmup_asr
 from argparse import Namespace
 import sys
 
+def update_with_kwargs(_dict, kwargs):
+    _dict.update({
+        k: v for k, v in kwargs.items() if k in _dict
+    })
+    return _dict
+
 class TranscriptionEngine:
     _instance = None
     _initialized = False
@@ -21,76 +26,48 @@ class TranscriptionEngine:
         if TranscriptionEngine._initialized:
             return
 
-        defaults = {
+        global_params = {
             "host": "localhost",
             "port": 8000,
-            "warmup_file": None,
             "diarization": False,
             "punctuation_split": False,
-            "min_chunk_size": 0.5,
-            "model": "tiny",
-            "model_cache_dir": None,
-            "model_dir": None,
-            "lan": "auto",
-            "task": "transcribe",
             "target_language": "",
-            "backend": "faster-whisper",
             "vac": True,
             "vac_chunk_size": 0.04,
             "log_level": "DEBUG",
             "ssl_certfile": None,
             "ssl_keyfile": None,
+            "forwarded_allow_ips": None,
             "transcription": True,
             "vad": True,
             "pcm_input": False,
-            
-            # whisperstreaming params:
-            "buffer_trimming": "segment",
-            "confidence_validation": False,
-            "buffer_trimming_sec": 15,
-            
-            # simulstreaming params:
-            "disable_fast_encoder": False,
-            "frame_threshold": 25,
-            "beams": 1,
-            "decoder_type": None,
-            "audio_max_len": 20.0,
-            "audio_min_len": 0.0,
-            "cif_ckpt_path": None,
-            "never_fire": False,
-            "init_prompt": None,
-            "static_init_prompt": None,
-            "max_context_tokens": None,
-            "model_path": './base.pt',
-            "diarization_backend": "sortformer",
-            
-            # diarization params:
             "disable_punctuation_split" : False,
-            "segmentation_model": "pyannote/segmentation-3.0",
+            "diarization_backend": "sortformer",
-            "embedding_model": "pyannote/embedding",  
-            
-            # translation params:
-            "nllb_backend": "ctranslate2",
-            "nllb_size": "600M"
         }
+        global_params = update_with_kwargs(global_params, kwargs)
 
-        config_dict = {**defaults, **kwargs}
+        transcription_common_params = {
+            "backend": "simulstreaming",
+            "warmup_file": None,
+            "min_chunk_size": 0.5,
+            "model_size": "tiny",
+            "model_cache_dir": None,
+            "model_dir": None,
+            "lan": "auto",
+            "task": "transcribe",
+        }
+        transcription_common_params = update_with_kwargs(transcription_common_params, kwargs)                                            
 
+        if transcription_common_params['model_size'].endswith(".en"):
+            transcription_common_params["lan"] = "en"
         if 'no_transcription' in kwargs:
-            config_dict['transcription'] = not kwargs['no_transcription']
+            global_params['transcription'] = not global_params['no_transcription']
         if 'no_vad' in kwargs:
-            config_dict['vad'] = not kwargs['no_vad']
+            global_params['vad'] = not kwargs['no_vad']
         if 'no_vac' in kwargs:
-            config_dict['vac'] = not kwargs['no_vac']
+            global_params['vac'] = not kwargs['no_vac']
-        
-        config_dict.pop('no_transcription', None)
-        config_dict.pop('no_vad', None)
 
-        if 'language' in kwargs:
+        self.args = Namespace(**{**global_params, **transcription_common_params})
-            config_dict['lan'] = kwargs['language']
-        config_dict.pop('language', None) 
-
-        self.args = Namespace(**config_dict)
         
         self.asr = None
         self.tokenizer = None
@@ -104,71 +81,79 @@ class TranscriptionEngine:
         if self.args.transcription:
             if self.args.backend == "simulstreaming": 
                 from whisperlivekit.simul_whisper import SimulStreamingASR
-                self.tokenizer = None
-                simulstreaming_kwargs = {}
-                for attr in ['frame_threshold', 'beams', 'decoder_type', 'audio_max_len', 'audio_min_len', 
-                            'cif_ckpt_path', 'never_fire', 'init_prompt', 'static_init_prompt', 
-                            'max_context_tokens', 'model_path', 'warmup_file', 'preload_model_count', 'disable_fast_encoder']:
-                    if hasattr(self.args, attr):
-                        simulstreaming_kwargs[attr] = getattr(self.args, attr)
-        
-                # Add segment_length from min_chunk_size
-                simulstreaming_kwargs['segment_length'] = getattr(self.args, 'min_chunk_size', 0.5)
-                simulstreaming_kwargs['task'] = self.args.task
                 
-                size = self.args.model
+                simulstreaming_params = {
+                    "disable_fast_encoder": False,
+                    "custom_alignment_heads": None,
+                    "frame_threshold": 25,
+                    "beams": 1,
+                    "decoder_type": None,
+                    "audio_max_len": 20.0,
+                    "audio_min_len": 0.0,
+                    "cif_ckpt_path": None,
+                    "never_fire": False,
+                    "init_prompt": None,
+                    "static_init_prompt": None,
+                    "max_context_tokens": None,
+                    "model_path": './base.pt',
+                    "preload_model_count": 1,
+                }
+                simulstreaming_params = update_with_kwargs(simulstreaming_params, kwargs)
+                
+                self.tokenizer = None        
                 self.asr = SimulStreamingASR(
-                    modelsize=size,
+                    **transcription_common_params, **simulstreaming_params
-                    lan=self.args.lan,
-                    cache_dir=getattr(self.args, 'model_cache_dir', None),
-                    model_dir=getattr(self.args, 'model_dir', None),
-                    **simulstreaming_kwargs
                 )
-
             else:
-                self.asr, self.tokenizer = backend_factory(self.args)
+                
-                warmup_asr(self.asr, self.args.warmup_file) #for simulstreaming, warmup should be done in the online class not here
+                whisperstreaming_params = {
+                    "buffer_trimming": "segment",
+                    "confidence_validation": False,
+                    "buffer_trimming_sec": 15,
+                }
+                whisperstreaming_params = update_with_kwargs(whisperstreaming_params, kwargs)
+                
+                self.asr = backend_factory(
+                    **transcription_common_params, **whisperstreaming_params
+                )
 
         if self.args.diarization:
             if self.args.diarization_backend == "diart":
                 from whisperlivekit.diarization.diart_backend import DiartDiarization
+                diart_params = {
+                    "segmentation_model": "pyannote/segmentation-3.0",
+                    "embedding_model": "pyannote/embedding",
+                }
+                diart_params = update_with_kwargs(diart_params, kwargs)
                 self.diarization_model = DiartDiarization(
                     block_duration=self.args.min_chunk_size,
-                    segmentation_model_name=self.args.segmentation_model,
+                    **diart_params
-                    embedding_model_name=self.args.embedding_model
                 )
             elif self.args.diarization_backend == "sortformer":
                 from whisperlivekit.diarization.sortformer_backend import SortformerDiarization
                 self.diarization_model = SortformerDiarization()
-            else:
-                raise ValueError(f"Unknown diarization backend: {self.args.diarization_backend}")
         
         self.translation_model = None
         if self.args.target_language:
-            if self.args.lan == 'auto':
+            if self.args.lan == 'auto' and self.args.backend != "simulstreaming":
-                raise Exception('Translation cannot be set with language auto')
+                raise Exception('Translation cannot be set with language auto when transcription backend is not simulstreaming')
             else:
                 from whisperlivekit.translation.translation import load_model
-                self.translation_model = load_model([self.args.lan], backend=self.args.nllb_backend, model_size=self.args.nllb_size) #in the future we want to handle different languages for different speakers
+                translation_params = { 
+                    "nllb_backend": "ctranslate2",
+                    "nllb_size": "600M"
+                }
+                translation_params = update_with_kwargs(translation_params, kwargs)
+                self.translation_model = load_model([self.args.lan], **translation_params) #in the future we want to handle different languages for different speakers
         TranscriptionEngine._initialized = True
 
 
-
+def online_factory(args, asr):
-def online_factory(args, asr, tokenizer, logfile=sys.stderr):
     if args.backend == "simulstreaming":    
         from whisperlivekit.simul_whisper import SimulStreamingOnlineProcessor
-        online = SimulStreamingOnlineProcessor(
+        online = SimulStreamingOnlineProcessor(asr)
-            asr,
-            logfile=logfile,
-        )
     else:
-        online = OnlineASRProcessor(
+        online = OnlineASRProcessor(asr)
-            asr,
-            tokenizer,
-            logfile=logfile,
-            buffer_trimming=(args.buffer_trimming, args.buffer_trimming_sec),
-            confidence_validation = args.confidence_validation
-        )
     return online
   
   

whisperlivekit/diarization/diart_backend.py

@@ -242,7 +242,7 @@ class DiartDiarization:
                         token.speaker = extract_number(segment.speaker) + 1
         else:
             tokens = add_speaker_to_tokens(segments, tokens)
-        return tokens, segments[-1]
+        return tokens
         
 def concatenate_speakers(segments):
     segments_concatenated = [{"speaker": 1, "begin": 0.0, "end": 0.0}]

whisperlivekit/diarization/sortformer_backend.py

@@ -296,7 +296,7 @@ class SortformerDiarizationOnline:
         
         if not segments or not tokens:
             logger.debug("No segments or tokens available for speaker assignment")
-            return tokens, None
+            return tokens
         
         logger.debug(f"Assigning speakers to {len(tokens)} tokens using {len(segments)} segments")
         use_punctuation_split = False
@@ -313,7 +313,7 @@ class SortformerDiarizationOnline:
             # Use punctuation-aware assignment (similar to diart_backend)
             tokens = self._add_speaker_to_tokens_with_punctuation(segments, tokens)
         
-        return tokens, segments[-1]
+        return tokens
 
     def _add_speaker_to_tokens_with_punctuation(self, segments: List[SpeakerSegment], tokens: list) -> list:
         """

whisperlivekit/parse_args.py

@@ -89,6 +89,7 @@ def parse_args():
         "--model",
         type=str,
         default="small",
+        dest='model_size',
         help="Name size of the Whisper model to use (default: tiny). Suggested values: tiny.en,tiny,base.en,base,small.en,small,medium.en,medium,large-v1,large-v2,large-v3,large,large-v3-turbo. The model is automatically downloaded from the model hub if not present in model cache dir.",
     )
     
@@ -109,6 +110,7 @@ def parse_args():
         "--language",
         type=str,
         default="auto",
+        dest='lan',
         help="Source language code, e.g. en,de,cs, or 'auto' for language detection.",
     )
     parser.add_argument(
@@ -173,6 +175,7 @@ def parse_args():
     )
     parser.add_argument("--ssl-certfile", type=str, help="Path to the SSL certificate file.", default=None)
     parser.add_argument("--ssl-keyfile", type=str, help="Path to the SSL private key file.", default=None)
+    parser.add_argument("--forwarded-allow-ips", type=str, help="Allowed ips for reverse proxying.", default=None)
     parser.add_argument(
         "--pcm-input",
         action="store_true",
@@ -189,6 +192,13 @@ def parse_args():
         dest="disable_fast_encoder",
         help="Disable Faster Whisper or MLX Whisper backends for encoding (if installed). Slower but helpful when GPU memory is limited",
     )
+
+    simulstreaming_group.add_argument(
+        "--custom-alignment-heads",
+        type=str,
+        default=None,
+        help="Use your own alignment heads, useful when `--model-dir` is used",
+    )
     
     simulstreaming_group.add_argument(
         "--frame-threshold",

whisperlivekit/remove_silences.py

@@ -78,16 +78,8 @@ def no_token_to_silence(tokens):
     return new_tokens
             
 def ends_with_silence(tokens, current_time, vac_detected_silence):
-    end_w_silence = False
-    if not tokens:
-        return [], end_w_silence
     last_token = tokens[-1]
-    if tokens and current_time and (
+    if  vac_detected_silence or (current_time - last_token.end >= END_SILENCE_DURATION):
-        current_time - last_token.end >= END_SILENCE_DURATION 
-        or
-        (current_time - last_token.end >= 3 and vac_detected_silence)
-        ):
-        end_w_silence = True
         if last_token.speaker == -2:
             last_token.end = current_time
         else:
@@ -99,12 +91,14 @@ def ends_with_silence(tokens, current_time, vac_detected_silence):
                     probability=0.95
                 )
             )
-    return tokens, end_w_silence
+    return tokens
     
 
 def handle_silences(tokens, current_time, vac_detected_silence):
+    if not tokens:
+        return []
     tokens = blank_to_silence(tokens) #useful for simulstreaming backend which tends to generate [BLANK_AUDIO] text
     tokens = no_token_to_silence(tokens)
-    tokens, end_w_silence = ends_with_silence(tokens, current_time, vac_detected_silence)
+    tokens = ends_with_silence(tokens, current_time, vac_detected_silence)
-    return tokens, end_w_silence
+    return tokens
      

whisperlivekit/results_formater.py

@@ -7,6 +7,8 @@ logger = logging.getLogger(__name__)
 logger.setLevel(logging.DEBUG)
 
 CHECK_AROUND = 4
+DEBUG = False
+
 
 def is_punctuation(token):
     if token.is_punctuation():
@@ -30,95 +32,96 @@ def next_speaker_change(i, tokens, speaker):
     
 def new_line(
     token,
-    speaker,
-    debug_info = ""
 ):
     return Line(
-        speaker = speaker,
+        speaker = token.corrected_speaker,
-        text = token.text + debug_info,
+        text = token.text + (f"[{format_time(token.start)} : {format_time(token.end)}]" if DEBUG else ""),
         start = token.start,
         end = token.end,
+        detected_language=token.detected_language
     )
 
-def append_token_to_last_line(lines, sep, token, debug_info):
+def append_token_to_last_line(lines, sep, token):
-    if token.text:
+    if not lines:
-        lines[-1].text += sep + token.text + debug_info
+        lines.append(new_line(token))
-        lines[-1].end = token.end
+    else:
+        if token.text:
+            lines[-1].text += sep + token.text + (f"[{format_time(token.start)} : {format_time(token.end)}]" if DEBUG else "")
+            lines[-1].end = token.end
+        if not lines[-1].detected_language and token.detected_language:
+            lines[-1].detected_language = token.detected_language
+            
 
-def format_output(state, silence, current_time, args, debug, sep):
+def format_output(state, silence, current_time, args, sep):
     diarization = args.diarization
     disable_punctuation_split = args.disable_punctuation_split
     tokens = state.tokens
     translated_segments = state.translated_segments # Here we will attribute the speakers only based on the timestamps of the segments
-    end_attributed_speaker = state.end_attributed_speaker
+    last_validated_token = state.last_validated_token
     
-    previous_speaker = -1
+    previous_speaker = 1
-    lines = []
     undiarized_text = []
-    tokens, end_w_silence = handle_silences(tokens, current_time, silence)
+    tokens = handle_silences(tokens, current_time, silence)
     last_punctuation = None
-    for i, token in enumerate(tokens):
+    for i, token in enumerate(tokens[last_validated_token:]):
-        speaker = token.speaker
+        speaker = int(token.speaker)
-        if not diarization and speaker == -1: #Speaker -1 means no attributed by diarization. In the frontend, it should appear under 'Speaker 1'
+        token.corrected_speaker = speaker
-            speaker = 1
+        if not diarization:
-        if diarization and not tokens[-1].speaker == -2:
+            if speaker == -1: #Speaker -1 means no attributed by diarization. In the frontend, it should appear under 'Speaker 1'
-            if (speaker in [-1, 0]) and token.end >= end_attributed_speaker:
+                token.corrected_speaker = 1
-                undiarized_text.append(token.text)
+                token.validated_speaker = True
-                continue
-            elif (speaker in [-1, 0]) and token.end < end_attributed_speaker:
-                speaker = previous_speaker
-        debug_info = ""
-        if debug:
-            debug_info = f"[{format_time(token.start)} : {format_time(token.end)}]"
-            
-        if not lines:
-            lines.append(new_line(token, speaker, debug_info = ""))
-            continue
         else:
-            previous_speaker = lines[-1].speaker
+            # if token.end > end_attributed_speaker and token.speaker != -2:
-        
+            #     if tokens[-1].speaker == -2:  #if it finishes by a silence, we want to append the undiarized text to the last speaker.
-        if is_punctuation(token):
+            #         token.corrected_speaker = previous_speaker
-            last_punctuation = i
+            #     else:
-            
+            #         undiarized_text.append(token.text)
-        
+            #         continue
-        if last_punctuation == i-1:
+            # else:
-            if speaker != previous_speaker:
+                if is_punctuation(token):
-                # perfect, diarization perfectly aligned
+                    last_punctuation = i  
-                lines.append(new_line(token, speaker, debug_info = ""))
+                
-                last_punctuation, next_punctuation = None, None
+                if last_punctuation == i-1:
-                continue
+                    if token.speaker != previous_speaker:
-            
+                        token.validated_speaker = True
-            speaker_change_pos, new_speaker = next_speaker_change(i, tokens, speaker)
+                        # perfect, diarization perfectly aligned
-            if speaker_change_pos:
+                        last_punctuation = None
-                # Corrects delay:
+                    else:
-                # That was the idea. Okay haha |SPLIT SPEAKER| that's a good one 
+                        speaker_change_pos, new_speaker = next_speaker_change(i, tokens, speaker)
-                # should become:
+                        if speaker_change_pos:
-                # That was the idea. |SPLIT SPEAKER| Okay haha that's a good one 
+                            # Corrects delay:
-                lines.append(new_line(token, new_speaker, debug_info = ""))
+                            # That was the idea. <Okay> haha |SPLIT SPEAKER| that's a good one 
-            else:
+                            # should become:
-                # No speaker change to come
+                            # That was the idea. |SPLIT SPEAKER| <Okay> haha that's a good one 
-                append_token_to_last_line(lines, sep, token, debug_info)
+                            token.corrected_speaker = new_speaker
-            continue
+                            token.validated_speaker = True
-        
+                elif speaker != previous_speaker:
+                    if not (speaker == -2 or previous_speaker == -2):
+                        if next_punctuation_change(i, tokens):
+                            # Corrects advance:
+                            # Are you |SPLIT SPEAKER| <okay>? yeah, sure. Absolutely 
+                            # should become:
+                            # Are you <okay>? |SPLIT SPEAKER| yeah, sure. Absolutely 
+                            token.corrected_speaker = previous_speaker
+                            token.validated_speaker = True
+                        else: #Problematic, except if the language has no punctuation. We append to previous line, except if disable_punctuation_split is set to True.
+                            if not disable_punctuation_split:
+                                token.corrected_speaker = previous_speaker
+                                token.validated_speaker = False
+        if token.validated_speaker:
+            state.last_validated_token = i
+        previous_speaker = token.corrected_speaker  
 
-        if speaker != previous_speaker:
+    previous_speaker = 1
-            if speaker == -2 or previous_speaker == -2: #silences can happen anytime
+    
-                lines.append(new_line(token, speaker, debug_info = ""))
+    lines = []
-                continue
+    for token in tokens:
-            elif next_punctuation_change(i, tokens):
+        if int(token.corrected_speaker) != int(previous_speaker):
-                # Corrects advance:
+            lines.append(new_line(token))
-                # Are you |SPLIT SPEAKER| okay? yeah, sure. Absolutely 
+        else:
-                # should become:
+            append_token_to_last_line(lines, sep, token)
-                # Are you okay? |SPLIT SPEAKER| yeah, sure. Absolutely 
+
-                append_token_to_last_line(lines, sep, token, debug_info)
+        previous_speaker = token.corrected_speaker        
-                continue
-            else: #we create a new speaker, but that's no ideal. We are not sure about the split. We prefer to append to previous line
-                if disable_punctuation_split:
-                    lines.append(new_line(token, speaker, debug_info = ""))
-                    continue
-                pass
-            
-        append_token_to_last_line(lines, sep, token, debug_info)
 
     if lines and translated_segments:
         unassigned_translated_segments = []
@@ -154,4 +157,4 @@ def format_output(state, silence, current_time, args, debug, sep):
     if state.buffer_transcription and lines:
         lines[-1].end = max(state.buffer_transcription.end, lines[-1].end)
         
-    return lines, undiarized_text, end_w_silence
+    return lines, undiarized_text

whisperlivekit/simul_whisper/backend.py

@@ -4,7 +4,7 @@ import logging
 from typing import List, Tuple, Optional
 import logging
 import platform
-from whisperlivekit.timed_objects import ASRToken, Transcript, SpeakerSegment
+from whisperlivekit.timed_objects import ASRToken, Transcript, ChangeSpeaker
 from whisperlivekit.warmup import load_file
 from .whisper import load_model, tokenizer
 from .whisper.audio import TOKENS_PER_SECOND
@@ -22,11 +22,9 @@ try:
     HAS_MLX_WHISPER = True
 except ImportError:
     if platform.system() == "Darwin" and platform.machine() == "arm64":
-        print(f"""
+        print(f"""{"="*50}
-            {"="*50}
+MLX Whisper not found but you are on Apple Silicon. Consider installing mlx-whisper for better performance: pip install mlx-whisper
-            MLX Whisper not found but you are on Apple Silicon. Consider installing mlx-whisper for better performance: pip install mlx-whisper
+{"="*50}""")
-            {"="*50}
-            """)
     HAS_MLX_WHISPER = False
 if HAS_MLX_WHISPER:
     HAS_FASTER_WHISPER = False
@@ -47,7 +45,6 @@ class SimulStreamingOnlineProcessor:
         self,
         asr,
         logfile=sys.stderr,
-        warmup_file=None
     ):        
         self.asr = asr
         self.logfile = logfile
@@ -93,14 +90,16 @@ class SimulStreamingOnlineProcessor:
         self.end = audio_stream_end_time #Only to be aligned with what happens in whisperstreaming backend.
         self.model.insert_audio(audio_tensor)
 
-    def on_new_speaker(self, last_segment: SpeakerSegment):
+    def new_speaker(self, change_speaker: ChangeSpeaker):
-            self.model.on_new_speaker(last_segment)
+            self.process_iter(is_last=True)
             self.model.refresh_segment(complete=True)
-
+            self.model.speaker = change_speaker.speaker
+            self.global_time_offset = change_speaker.start
+            
     def get_buffer(self):
         concat_buffer = Transcript.from_tokens(tokens= self.buffer, sep='')
         return concat_buffer
-            
+
     def process_iter(self, is_last=False) -> Tuple[List[ASRToken], float]:
         """
         Process accumulated audio chunks using SimulStreaming.
@@ -108,9 +107,13 @@ class SimulStreamingOnlineProcessor:
         Returns a tuple: (list of committed ASRToken objects, float representing the audio processed up to time).
         """
         try:
-            timestamped_words, timestamped_buffer_language = self.model.infer(is_last=is_last)
+            timestamped_words = self.model.infer(is_last=is_last)
-            self.buffer = timestamped_buffer_language
+            if self.model.cfg.language == "auto" and timestamped_words and timestamped_words[0].detected_language == None:
+                self.buffer.extend(timestamped_words)
+                return [], self.end
+            
             self.committed.extend(timestamped_words)
+            self.buffer = []
             return timestamped_words, self.end
 
             
@@ -140,31 +143,20 @@ class SimulStreamingASR():
     """SimulStreaming backend with AlignAtt policy."""
     sep = ""
 
-    def __init__(self, lan, modelsize=None, cache_dir=None, model_dir=None, logfile=sys.stderr, **kwargs):
+    def __init__(self, logfile=sys.stderr, **kwargs):
         self.logfile = logfile
         self.transcribe_kargs = {}
-        self.original_language = lan
         
-        self.model_path = kwargs.get('model_path', './large-v3.pt')
+        for key, value in kwargs.items():
-        self.frame_threshold = kwargs.get('frame_threshold', 25)
+            setattr(self, key, value)
-        self.audio_max_len = kwargs.get('audio_max_len', 20.0)
+
-        self.audio_min_len = kwargs.get('audio_min_len', 0.0)
+        if self.decoder_type is None:
-        self.segment_length = kwargs.get('segment_length', 0.5)
+            self.decoder_type = 'greedy' if self.beams == 1 else 'beam'
-        self.beams = kwargs.get('beams', 1)
+
-        self.decoder_type = kwargs.get('decoder_type', 'greedy' if self.beams == 1 else 'beam')
-        self.task = kwargs.get('task', 'transcribe')
-        self.cif_ckpt_path = kwargs.get('cif_ckpt_path', None)
-        self.never_fire = kwargs.get('never_fire', False)
-        self.init_prompt = kwargs.get('init_prompt', None)
-        self.static_init_prompt = kwargs.get('static_init_prompt', None)
-        self.max_context_tokens = kwargs.get('max_context_tokens', None)
-        self.warmup_file = kwargs.get('warmup_file', None)
-        self.preload_model_count = kwargs.get('preload_model_count', 1)
-        self.disable_fast_encoder = kwargs.get('disable_fast_encoder', False)
         self.fast_encoder = False
-        if model_dir is not None:
+        if self.model_dir is not None:
-            self.model_path = model_dir
+            self.model_path = self.model_dir
-        elif modelsize is not None:
+        elif self.model_size is not None:
             model_mapping = {
                 'tiny': './tiny.pt',
                 'base': './base.pt',
@@ -179,13 +171,13 @@ class SimulStreamingASR():
                 'large-v3': './large-v3.pt',
                 'large': './large-v3.pt'
             }
-            self.model_path = model_mapping.get(modelsize, f'./{modelsize}.pt')
+            self.model_path = model_mapping.get(self.model_size, f'./{self.model_size}.pt')
         
         self.cfg = AlignAttConfig(
                 model_path=self.model_path,
-                segment_length=self.segment_length,
+                segment_length=self.min_chunk_size,
                 frame_threshold=self.frame_threshold,
-                language=self.original_language,
+                language=self.lan,
                 audio_max_len=self.audio_max_len,
                 audio_min_len=self.audio_min_len,
                 cif_ckpt_path=self.cif_ckpt_path,
@@ -204,8 +196,12 @@ class SimulStreamingASR():
         else:
             self.tokenizer = None
         
-        self.model_name = os.path.basename(self.cfg.model_path).replace(".pt", "")
+        if self.model_dir:
-        self.model_path = os.path.dirname(os.path.abspath(self.cfg.model_path))
+            self.model_name = self.model_dir
+            self.model_path = None
+        else:
+            self.model_name = os.path.basename(self.cfg.model_path).replace(".pt", "")
+            self.model_path = os.path.dirname(os.path.abspath(self.cfg.model_path))
     
         self.mlx_encoder, self.fw_encoder = None, None
         if not self.disable_fast_encoder:
@@ -227,7 +223,12 @@ class SimulStreamingASR():
 
 
     def load_model(self):
-        whisper_model = load_model(name=self.model_name, download_root=self.model_path, decoder_only=self.fast_encoder)
+        whisper_model = load_model(
+            name=self.model_name,
+            download_root=self.model_path,
+            decoder_only=self.fast_encoder,
+            custom_alignment_heads=self.custom_alignment_heads
+            )
         warmup_audio = load_file(self.warmup_file)
         if warmup_audio is not None:
             warmup_audio = torch.from_numpy(warmup_audio).float()
@@ -243,7 +244,7 @@ class SimulStreamingASR():
             else:
                 # For standard encoder, use the original transcribe warmup
                 warmup_audio = load_file(self.warmup_file)
-                whisper_model.transcribe(warmup_audio, language=self.original_language if self.original_language != 'auto' else None)
+                whisper_model.transcribe(warmup_audio, language=self.lan if self.lan != 'auto' else None)
         return whisper_model
     
     def get_new_model_instance(self):

whisperlivekit/simul_whisper/simul_whisper.py

@@ -66,7 +66,7 @@ class PaddedAlignAttWhisper:
             self.fw_feature_extractor = FeatureExtractor(feature_size=self.model.dims.n_mels)
             
         logger.info(f"Model dimensions: {self.model.dims}")
-
+        self.speaker = -1
         self.decode_options = DecodingOptions(
             language = cfg.language, 
             without_timestamps = True,
@@ -78,7 +78,6 @@ class PaddedAlignAttWhisper:
         self.detected_language = cfg.language if cfg.language != "auto" else None
         self.global_time_offset = 0.0
         self.reset_tokenizer_to_auto_next_call = False
-        self.sentence_start_time = 0.0
         
         self.max_text_len = self.model.dims.n_text_ctx
         self.num_decoder_layers = len(self.model.decoder.blocks)
@@ -153,7 +152,7 @@ class PaddedAlignAttWhisper:
         
         self.last_attend_frame = -self.cfg.rewind_threshold
         self.cumulative_time_offset = 0.0
-        self.sentence_start_time = self.cumulative_time_offset + self.segments_len()
+        self.first_timestamp = None
 
         if self.cfg.max_context_tokens is None:
             self.max_context_tokens = self.max_text_len
@@ -261,7 +260,6 @@ class PaddedAlignAttWhisper:
         self.init_context()
         logger.debug(f"Context: {self.context}")
         if not complete and len(self.segments) > 2:
-            logger.debug("keeping last two segments because they are and it is not complete.")
             self.segments = self.segments[-2:]
         else:
             logger.debug("removing all segments.")
@@ -434,18 +432,19 @@ class PaddedAlignAttWhisper:
         end_encode = time()
         # print('Encoder duration:', end_encode-beg_encode)
                 
-        if self.cfg.language == "auto" and self.detected_language is None:
+        if self.cfg.language == "auto" and self.detected_language is None and self.first_timestamp:
-            seconds_since_start = (self.cumulative_time_offset + self.segments_len()) - self.sentence_start_time
+            seconds_since_start = self.segments_len() - self.first_timestamp
-            if seconds_since_start >= 3.0:
+            if seconds_since_start >= 2.0:
                 language_tokens, language_probs = self.lang_id(encoder_feature) 
                 top_lan, p = max(language_probs[0].items(), key=lambda x: x[1])
                 print(f"Detected language: {top_lan} with p={p:.4f}")
                 self.create_tokenizer(top_lan)
-                self.refresh_segment(complete=True)
+                self.last_attend_frame = -self.cfg.rewind_threshold
+                self.cumulative_time_offset = 0.0
+                self.init_tokens()
+                self.init_context()
                 self.detected_language = top_lan
                 logger.info(f"Tokenizer language: {self.tokenizer.language}, {self.tokenizer.sot_sequence_including_notimestamps}")
-            else:
-                logger.debug(f"Skipping language detection: {seconds_since_start:.2f}s < 3.0s")
 
         self.trim_context()
         current_tokens = self._current_tokens()
@@ -590,6 +589,10 @@ class PaddedAlignAttWhisper:
         
         self._clean_cache()
 
+        if len(l_absolute_timestamps) >=2 and self.first_timestamp is None:
+            self.first_timestamp = l_absolute_timestamps[0]
+            
+
         timestamped_words = []
         timestamp_idx = 0
         for word, word_tokens in zip(split_words, split_tokens):
@@ -604,15 +607,11 @@ class PaddedAlignAttWhisper:
                     end=current_timestamp + 0.1,
                     text= word,
                     probability=0.95,
-                    language=self.detected_language
+                    speaker=self.speaker,
+                    detected_language=self.detected_language
                 ).with_offset(
                     self.global_time_offset
             )
             timestamped_words.append(timestamp_entry)
         
-        if self.detected_language is None and self.cfg.language == "auto":
+        return timestamped_words
-            timestamped_buffer_language, timestamped_words = timestamped_words, []
-        else:
-            timestamped_buffer_language = []
-        
-        return timestamped_words, timestamped_buffer_language

whisperlivekit/simul_whisper/whisper/__init__.py

@@ -105,7 +105,8 @@ def load_model(
     device: Optional[Union[str, torch.device]] = None,
     download_root: str = None,
     in_memory: bool = False,
-    decoder_only=False
+    decoder_only=False,
+    custom_alignment_heads=None
 ) -> Whisper:
     """
     Load a Whisper ASR model
@@ -135,15 +136,17 @@ def load_model(
         download_root = os.path.join(os.getenv("XDG_CACHE_HOME", default), "whisper")
 
     if name in _MODELS:
-        checkpoint_file = _download(_MODELS[name], download_root, in_memory)
+        checkpoint_file = _download(_MODELS[name], download_root, in_memory)        
-        alignment_heads = _ALIGNMENT_HEADS[name]
     elif os.path.isfile(name):
         checkpoint_file = open(name, "rb").read() if in_memory else name
-        alignment_heads = None
     else:
         raise RuntimeError(
             f"Model {name} not found; available models = {available_models()}"
         )
+        
+    alignment_heads = _ALIGNMENT_HEADS.get(name, None)
+    if custom_alignment_heads:
+        alignment_heads = custom_alignment_heads.encode()
 
     with (
         io.BytesIO(checkpoint_file) if in_memory else open(checkpoint_file, "rb")

whisperlivekit/timed_objects.py

@@ -17,7 +17,7 @@ class TimedText:
     speaker: Optional[int] = -1
     probability: Optional[float] = None
     is_dummy: Optional[bool] = False
-    language: str = None
+    detected_language: Optional[str] = None
     
     def is_punctuation(self):
         return self.text.strip() in PUNCTUATION_MARKS
@@ -41,11 +41,17 @@ class TimedText:
         return bool(self.text)
 
 
-@dataclass
+@dataclass()
 class ASRToken(TimedText):
+    
+    corrected_speaker: Optional[int] = -1
+    validated_speaker: bool = False
+    validated_text: bool = False
+    validated_language: bool = False
+    
     def with_offset(self, offset: float) -> "ASRToken":
         """Return a new token with the time offset added."""
-        return ASRToken(self.start + offset, self.end + offset, self.text, self.speaker, self.probability)
+        return ASRToken(self.start + offset, self.end + offset, self.text, self.speaker, self.probability, detected_language=self.detected_language)
 
 @dataclass
 class Sentence(TimedText):
@@ -123,11 +129,10 @@ class Silence():
 @dataclass
 class Line(TimedText):
     translation: str = ''
-    detected_language: str = None
     
     def to_dict(self):
         _dict = {
-            'speaker': int(self.speaker),
+            'speaker': int(self.speaker) if self.speaker != -1 else 1,
             'text': self.text,
             'start': format_time(self.start),
             'end': format_time(self.end),
@@ -152,7 +157,7 @@ class FrontData():
     def to_dict(self):
         _dict = {
             'status': self.status,
-            'lines': [line.to_dict() for line in self.lines],
+            'lines': [line.to_dict() for line in self.lines if (line.text or line.speaker == -2)],
             'buffer_transcription': self.buffer_transcription,
             'buffer_diarization': self.buffer_diarization,
             'remaining_time_transcription': self.remaining_time_transcription,
@@ -161,13 +166,18 @@ class FrontData():
         if self.error:
             _dict['error'] = self.error
         return _dict
-    
+
+@dataclass  
+class ChangeSpeaker:
+    speaker: int
+    start: int
+
 @dataclass  
 class State():
     tokens: list
+    last_validated_token: int
     translated_segments: list
     buffer_transcription: str
-    buffer_diarization: str
     end_buffer: float
     end_attributed_speaker: float
     remaining_time_transcription: float

whisperlivekit/translation/translation.py

@@ -3,7 +3,7 @@ import time
 import ctranslate2
 import torch
 import transformers
-from dataclasses import dataclass
+from dataclasses import dataclass, field
 import huggingface_hub
 from whisperlivekit.translation.mapping_languages import get_nllb_code
 from whisperlivekit.timed_objects import Translation
@@ -18,29 +18,46 @@ MIN_SILENCE_DURATION_DEL_BUFFER = 3 #After a silence of x seconds, we consider t
 @dataclass
 class TranslationModel():
     translator: ctranslate2.Translator
-    tokenizer: dict
     device: str
+    tokenizer: dict = field(default_factory=dict)
     backend_type: str = 'ctranslate2'
+    nllb_size: str = '600M'
+    
+    def get_tokenizer(self, input_lang):
+        if not self.tokenizer.get(input_lang, False):
+            self.tokenizer[input_lang] = transformers.AutoTokenizer.from_pretrained(
+                f"facebook/nllb-200-distilled-{self.nllb_size}",
+                src_lang=input_lang,
+                clean_up_tokenization_spaces=True
+            )
+        return self.tokenizer[input_lang]
+            
 
-def load_model(src_langs, backend='ctranslate2', model_size='600M'):
+def load_model(src_langs, nllb_backend='ctranslate2', nllb_size='600M'):
     device = "cuda" if torch.cuda.is_available() else "cpu"
-    MODEL = f'nllb-200-distilled-{model_size}-ctranslate2'
+    MODEL = f'nllb-200-distilled-{nllb_size}-ctranslate2'
-    if backend=='ctranslate2':
+    if nllb_backend=='ctranslate2':
         MODEL_GUY = 'entai2965'
         huggingface_hub.snapshot_download(MODEL_GUY + '/' + MODEL,local_dir=MODEL)
         translator = ctranslate2.Translator(MODEL,device=device)
-    elif backend=='transformers':
+    elif nllb_backend=='transformers':
-        translator = transformers.AutoModelForSeq2SeqLM.from_pretrained(f"facebook/nllb-200-distilled-{model_size}")
+        translator = transformers.AutoModelForSeq2SeqLM.from_pretrained(f"facebook/nllb-200-distilled-{nllb_size}")
     tokenizer = dict()
     for src_lang in src_langs:
-        tokenizer[src_lang] = transformers.AutoTokenizer.from_pretrained(MODEL, src_lang=src_lang, clean_up_tokenization_spaces=True)
+        if src_lang != 'auto':
+            tokenizer[src_lang] = transformers.AutoTokenizer.from_pretrained(MODEL, src_lang=src_lang, clean_up_tokenization_spaces=True)
 
-    return TranslationModel(
+    translation_model = TranslationModel(
         translator=translator,
         tokenizer=tokenizer,
-        backend_type=backend,
+        backend_type=nllb_backend,
-        device = device
+        device = device,
+        nllb_size = nllb_size
     )
+    for src_lang in src_langs:
+        if src_lang != 'auto':
+            translation_model.get_tokenizer(src_lang)
+    return translation_model
 
 class OnlineTranslation:
     def __init__(self, translation_model: TranslationModel, input_languages: list, output_languages: list):
@@ -63,16 +80,12 @@ class OnlineTranslation:
                     self.commited.extend(self.buffer[:i])
                     self.buffer = results[i:]
 
-    def translate(self, input, input_lang=None, output_lang=None):
+    def translate(self, input, input_lang, output_lang):
         if not input:
             return ""
-        if input_lang is None:
-            input_lang = self.input_languages[0]
-        if output_lang is None:
-            output_lang = self.output_languages[0]
         nllb_output_lang = get_nllb_code(output_lang)
             
-        tokenizer = self.translation_model.tokenizer[input_lang]
+        tokenizer = self.translation_model.get_tokenizer(input_lang)
         tokenizer_output = tokenizer(input, return_tensors="pt").to(self.translation_model.device)
         
         if self.translation_model.backend_type == 'ctranslate2':
@@ -90,7 +103,15 @@ class OnlineTranslation:
             text = ' '.join([token.text for token in tokens])
             start = tokens[0].start
             end = tokens[-1].end
-            translated_text = self.translate(text)
+            if self.input_languages[0] == 'auto':
+                input_lang = tokens[0].detected_language
+            else:
+                input_lang = self.input_languages[0]
+                
+            translated_text = self.translate(text,
+                                            input_lang,
+                                            self.output_languages[0]
+                                            )
             translation = Translation(
                 text=translated_text,
                 start=start,
@@ -136,7 +157,7 @@ if __name__ == '__main__':
     test = test_string.split(' ')
     step = len(test) // 3
     
-    shared_model = load_model([input_lang], backend='ctranslate2')
+    shared_model = load_model([input_lang], nllb_backend='ctranslate2')
     online_translation = OnlineTranslation(shared_model, input_languages=[input_lang], output_languages=[output_lang])
     
     beg_inference = time.time()    

whisperlivekit/web/live_transcription.css

@@ -72,6 +72,12 @@
   --label-trans-text: #111111;
 }
 
+html.is-extension
+{
+    width: 350px;
+    height: 500px;
+}
+
 body {
   font-family: ui-sans-serif, system-ui, sans-serif, 'Apple Color Emoji', 'Segoe UI Emoji', 'Segoe UI Symbol', 'Noto Color Emoji';
   margin: 0;
@@ -191,6 +197,14 @@ body {
   justify-content: center;
   align-items: center;
   gap: 15px;
+  position: relative;
+  flex-wrap: wrap;
+}
+
+.buttons-container {
+  display: flex;
+  align-items: center;
+  gap: 15px;
 }
 
 .settings {
@@ -200,6 +214,66 @@ body {
   gap: 12px;
 }
 
+.settings-toggle {
+  width: 40px;
+  height: 40px;
+  border: none;
+  border-radius: 50%;
+  background-color: var(--button-bg);
+  border: 1px solid var(--button-border);
+  cursor: pointer;
+  display: none;
+  align-items: center;
+  justify-content: center;
+  transition: all 0.2s ease;
+}
+
+.settings-toggle:hover {
+  background-color: var(--chip-bg);
+}
+
+.settings-toggle.active {
+  background-color: var(--chip-bg);
+}
+
+.settings-toggle img {
+  width: 20px;
+  height: 20px;
+}
+
+@media (max-width: 10000px) {
+  .settings-toggle {
+    display: flex;
+  }
+  
+  .settings {
+    display: none;
+    background: var(--bg);
+    border: 1px solid var(--border);
+    border-radius: 18px;
+    padding: 12px;
+  }
+  
+  .settings.visible {
+    display: flex;
+  }
+}
+
+@media (max-width: 600px) {
+  .settings-container {
+    flex-direction: column;
+    align-items: center;
+    gap: 10px;
+  }
+  
+  .buttons-container {
+    display: flex;
+    justify-content: center;
+    align-items: center;
+    gap: 15px;
+  }
+}
+
 .field {
   display: flex;
   flex-direction: column;
@@ -409,7 +483,6 @@ label {
 
 .buffer_diarization {
   color: var(--label-dia-text);
-  margin-left: 4px;
 }
 
 .buffer_transcription {
@@ -454,7 +527,7 @@ label {
 }
 
 /* for smaller screens */
-@media (max-width: 768px) {
+@media (max-width: 200px) {
   .header-container {
     padding: 15px;
   }
@@ -464,6 +537,10 @@ label {
     gap: 10px;
   }
   
+  .buttons-container {
+    gap: 10px;
+  }
+  
   .settings {
     justify-content: center;
     gap: 8px;
@@ -522,8 +599,6 @@ label {
 .label_language {
   background-color: var(--chip-bg);
   margin-bottom: 0px;
-  margin-top: 5px;
-  height: 18.5px;
   border-radius: 100px;
   padding: 2px 8px;
   margin-left: 10px;
@@ -534,22 +609,6 @@ label {
   color: var(--muted);
 }
 
-.label_language img {
-  width: 12px;
-  height: 12px;
-}
-
-.silence-icon {
-  width: 14px;
-  height: 14px;
-  vertical-align: text-bottom;
-}
-
-.speaker-icon {
-  width: 16px;
-  height: 16px;
-  vertical-align: text-bottom;
-}
 
 .speaker-badge {
   display: inline-flex;

whisperlivekit/web/live_transcription.html

@@ -5,23 +5,29 @@
     <meta charset="UTF-8" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>WhisperLiveKit</title>
-    <link rel="stylesheet" href="/web/live_transcription.css" />
+    <link rel="stylesheet" href="live_transcription.css" />
 </head>
 
 <body>
     <div class="header-container">
         <div class="settings-container">
-            <button id="recordButton">
+            <div class="buttons-container">
-                <div class="shape-container">
+                <button id="recordButton">
-                    <div class="shape"></div>
+                    <div class="shape-container">
-                </div>
+                        <div class="shape"></div>
-                <div class="recording-info">
-                    <div class="wave-container">
-                        <canvas id="waveCanvas"></canvas>
                     </div>
-                    <div class="timer">00:00</div>
+                    <div class="recording-info">
-                </div>
+                        <div class="wave-container">
-            </button>
+                            <canvas id="waveCanvas"></canvas>
+                        </div>
+                        <div class="timer">00:00</div>
+                    </div>
+                </button>
+
+                <button id="settingsToggle" class="settings-toggle" title="Show/hide settings">
+                    <img src="web/src/settings.svg" alt="Settings" />
+                </button>
+            </div>
 
             <div class="settings">
                 <div class="field">
@@ -67,7 +73,7 @@
         <div id="linesTranscript"></div>
     </div>
 
-    <script src="/web/live_transcription.js"></script>
+    <script src="live_transcription.js"></script>
 </body>
 
-</html>
+</html>

whisperlivekit/web/live_transcription.js

@@ -1,4 +1,8 @@
-/* Theme, WebSocket, recording, rendering logic extracted from inline script and adapted for segmented theme control and WS caption */
+const isExtension = typeof chrome !== 'undefined' && chrome.runtime && chrome.runtime.getURL;
+if (isExtension) {
+  document.documentElement.classList.add('is-extension');
+}
+const isWebContext = !isExtension;
 
 let isRecording = false;
 let websocket = null;
@@ -25,6 +29,8 @@ let selectedMicrophoneId = null;
 let serverUseAudioWorklet = null;
 let configReadyResolve;
 const configReady = new Promise((r) => (configReadyResolve = r));
+let outputAudioContext = null;
+let audioSource = null;
 
 waveCanvas.width = 60 * (window.devicePixelRatio || 1);
 waveCanvas.height = 30 * (window.devicePixelRatio || 1);
@@ -40,6 +46,26 @@ const timerElement = document.querySelector(".timer");
 const themeRadios = document.querySelectorAll('input[name="theme"]');
 const microphoneSelect = document.getElementById("microphoneSelect");
 
+const settingsToggle = document.getElementById("settingsToggle");
+const settingsDiv = document.querySelector(".settings");
+
+// if (isExtension) {
+//   chrome.runtime.onInstalled.addListener((details) => {
+//     if (details.reason.search(/install/g) === -1) {
+//       return;
+//     }
+//     chrome.tabs.create({
+//       url: chrome.runtime.getURL("welcome.html"),
+//       active: true
+//     });
+//   });
+// }
+
+const translationIcon = `<svg xmlns="http://www.w3.org/2000/svg" height="12px" viewBox="0 -960 960 960" width="12px" fill="#5f6368"><path d="m603-202-34 97q-4 11-14 18t-22 7q-20 0-32.5-16.5T496-133l152-402q5-11 15-18t22-7h30q12 0 22 7t15 18l152 403q8 19-4 35.5T868-80q-13 0-22.5-7T831-106l-34-96H603ZM362-401 188-228q-11 11-27.5 11.5T132-228q-11-11-11-28t11-28l174-174q-35-35-63.5-80T190-640h84q20 39 40 68t48 58q33-33 68.5-92.5T484-720H80q-17 0-28.5-11.5T40-760q0-17 11.5-28.5T80-800h240v-40q0-17 11.5-28.5T360-880q17 0 28.5 11.5T400-840v40h240q17 0 28.5 11.5T680-760q0 17-11.5 28.5T640-720h-76q-21 72-63 148t-83 116l96 98-30 82-122-125Zm266 129h144l-72-204-72 204Z"/></svg>`
+const silenceIcon = `<svg xmlns="http://www.w3.org/2000/svg" style="vertical-align: text-bottom;" height="14px" viewBox="0 -960 960 960" width="14px" fill="#5f6368"><path d="M514-556 320-752q9-3 19-5.5t21-2.5q66 0 113 47t47 113q0 11-1.5 22t-4.5 22ZM40-200v-32q0-33 17-62t47-44q51-26 115-44t141-18q26 0 49.5 2.5T456-392l-56-54q-9 3-19 4.5t-21 1.5q-66 0-113-47t-47-113q0-11 1.5-21t4.5-19L84-764q-11-11-11-28t11-28q12-12 28.5-12t27.5 12l675 685q11 11 11.5 27.5T816-80q-11 13-28 12.5T759-80L641-200h39q0 33-23.5 56.5T600-120H120q-33 0-56.5-23.5T40-200Zm80 0h480v-32q0-14-4.5-19.5T580-266q-36-18-92.5-36T360-320q-71 0-127.5 18T140-266q-9 5-14.5 14t-5.5 20v32Zm240 0Zm560-400q0 69-24.5 131.5T829-355q-12 14-30 15t-32-13q-13-13-12-31t12-33q30-38 46.5-85t16.5-98q0-51-16.5-97T767-781q-12-15-12.5-33t12.5-32q13-14 31.5-13.5T829-845q42 51 66.5 113.5T920-600Zm-182 0q0 32-10 61.5T700-484q-11 15-29.5 15.5T638-482q-13-13-13.5-31.5T633-549q6-11 9.5-24t3.5-27q0-14-3.5-27t-9.5-25q-9-17-8.5-35t13.5-31q14-14 32.5-13.5T700-716q18 25 28 54.5t10 61.5Z"/></svg>`;
+const languageIcon = `<svg xmlns="http://www.w3.org/2000/svg" height="12" viewBox="0 -960 960 960" width="12" fill="#5f6368"><path d="M480-80q-82 0-155-31.5t-127.5-86Q143-252 111.5-325T80-480q0-83 31.5-155.5t86-127Q252-817 325-848.5T480-880q83 0 155.5 31.5t127 86q54.5 54.5 86 127T880-480q0 82-31.5 155t-86 127.5q-54.5 54.5-127 86T480-80Zm0-82q26-36 45-75t31-83H404q12 44 31 83t45 75Zm-104-16q-18-33-31.5-68.5T322-320H204q29 50 72.5 87t99.5 55Zm208 0q56-18 99.5-55t72.5-87H638q-9 38-22.5 73.5T584-178ZM170-400h136q-3-20-4.5-39.5T300-480q0-21 1.5-40.5T306-560H170q-5 20-7.5 39.5T160-480q0 21 2.5 40.5T170-400Zm216 0h188q3-20 4.5-39.5T580-480q0-21-1.5-40.5T574-560H386q-3 20-4.5 39.5T380-480q0 21 1.5 40.5T386-400Zm268 0h136q5-20 7.5-39.5T800-480q0-21-2.5-40.5T790-560H654q3 20 4.5 39.5T660-480q0 21-1.5 40.5T654-400Zm-16-240h118q-29-50-72.5-87T584-782q18 33 31.5 68.5T638-640Zm-234 0h152q-12-44-31-83t-45-75q-26 36-45 75t-31 83Zm-200 0h118q9-38 22.5-73.5T376-782q-56 18-99.5 55T204-640Z"/></svg>`
+const speakerIcon = `<svg xmlns="http://www.w3.org/2000/svg" height="16px" style="vertical-align: text-bottom;" viewBox="0 -960 960 960" width="16px" fill="#5f6368"><path d="M480-480q-66 0-113-47t-47-113q0-66 47-113t113-47q66 0 113 47t47 113q0 66-47 113t-113 47ZM160-240v-32q0-34 17.5-62.5T224-378q62-31 126-46.5T480-440q66 0 130 15.5T736-378q29 15 46.5 43.5T800-272v32q0 33-23.5 56.5T720-160H240q-33 0-56.5-23.5T160-240Zm80 0h480v-32q0-11-5.5-20T700-306q-54-27-109-40.5T480-360q-56 0-111 13.5T260-306q-9 5-14.5 14t-5.5 20v32Zm240-320q33 0 56.5-23.5T560-640q0-33-23.5-56.5T480-720q-33 0-56.5 23.5T400-640q0 33 23.5 56.5T480-560Zm0-80Zm0 400Z"/></svg>`;
+
 function getWaveStroke() {
   const styles = getComputedStyle(document.documentElement);
   const v = styles.getPropertyValue("--wave-stroke").trim();
@@ -151,10 +177,16 @@ function fmt1(x) {
   return Number.isFinite(n) ? n.toFixed(1) : x;
 }
 
-// Default WebSocket URL computation
+let host, port, protocol;
-const host = window.location.hostname || "localhost";
+port = 8000;
-const port = window.location.port;
+if (isExtension) {
-const protocol = window.location.protocol === "https:" ? "wss" : "ws";
+    host = "localhost";
+    protocol = "ws";
+} else {
+    host = window.location.hostname || "localhost";
+    port = window.location.port;
+    protocol = window.location.protocol === "https:" ? "wss" : "ws";
+}
 const defaultWebSocketUrl = `${protocol}://${host}${port ? ":" + port : ""}/asr`;
 
 // Populate default caption and input
@@ -335,19 +367,17 @@ function renderLinesWithBuffer(
 
       let speakerLabel = "";
       if (item.speaker === -2) {
-        const silenceIcon = `<img class="silence-icon" src="/web/src/silence.svg" alt="Silence" />`;
         speakerLabel = `<span class="silence">${silenceIcon}<span id='timeInfo'>${timeInfo}</span></span>`;
       } else if (item.speaker == 0 && !isFinalizing) {
         speakerLabel = `<span class='loading'><span class="spinner"></span><span id='timeInfo'><span class="loading-diarization-value">${fmt1(
           remaining_time_diarization
         )}</span> second(s) of audio are undergoing diarization</span></span>`;
       } else if (item.speaker !== 0) {
-        const speakerIcon = `<img class="speaker-icon" src="/web/src/speaker.svg" alt="Speaker ${item.speaker}" />`;
         const speakerNum = `<span class="speaker-badge">${item.speaker}</span>`;
         speakerLabel = `<span id="speaker">${speakerIcon}${speakerNum}<span id='timeInfo'>${timeInfo}</span></span>`;
 
         if (item.detected_language) {
-          speakerLabel += `<span class="label_language"><img src="/web/src/language.svg" alt="Detected language" width="12" height="12" /><span>${item.detected_language}</span></span>`;
+          speakerLabel += `<span class="label_language">${languageIcon}<span>${item.detected_language}</span></span>`;
         }
       }
 
@@ -387,10 +417,13 @@ function renderLinesWithBuffer(
       }
       
       if (item.translation) {
-        currentLineText += `<div class="label_translation">
+        currentLineText += `
-          <img src="/web/src/translate.svg" alt="Translation" width="12" height="12" />
+            <div>
-          <span>${item.translation}</span>
+                <div class="label_translation">
-        </div>`;
+                    ${translationIcon}
+                    <span>${item.translation}</span>
+                </div>
+            </div>`;
       }
 
       return currentLineText.trim().length > 0 || speakerLabel.length > 0
@@ -465,11 +498,44 @@ async function startRecording() {
       console.log("Error acquiring wake lock.");
     }
 
-    const audioConstraints = selectedMicrophoneId 
+    let stream;
-      ? { audio: { deviceId: { exact: selectedMicrophoneId } } }
+    
-      : { audio: true };
+    // chromium extension. in the future, both chrome page audio and mic will be used
-
+    if (isExtension) {
-    const stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
+      try {
+        stream = await new Promise((resolve, reject) => {
+          chrome.tabCapture.capture({audio: true}, (s) => {
+            if (s) {
+              resolve(s);
+            } else {
+              reject(new Error('Tab capture failed or not available'));
+            }
+          });
+        });
+        
+        try {
+          outputAudioContext = new (window.AudioContext || window.webkitAudioContext)();
+          audioSource = outputAudioContext.createMediaStreamSource(stream);
+          audioSource.connect(outputAudioContext.destination);
+        } catch (audioError) {
+          console.warn('could not preserve system audio:', audioError);
+        }
+        
+        statusText.textContent = "Using tab audio capture.";
+      } catch (tabError) {
+        console.log('Tab capture not available, falling back to microphone', tabError);
+        const audioConstraints = selectedMicrophoneId
+          ? { audio: { deviceId: { exact: selectedMicrophoneId } } }
+          : { audio: true };
+        stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
+        statusText.textContent = "Using microphone audio.";
+      }
+    } else if (isWebContext) {
+      const audioConstraints = selectedMicrophoneId 
+        ? { audio: { deviceId: { exact: selectedMicrophoneId } } }
+        : { audio: true };
+      stream = await navigator.mediaDevices.getUserMedia(audioConstraints);
+    }
 
     audioContext = new (window.AudioContext || window.webkitAudioContext)();
     analyser = audioContext.createAnalyser();
@@ -603,6 +669,16 @@ async function stopRecording() {
     audioContext = null;
   }
 
+  if (audioSource) {
+    audioSource.disconnect();
+    audioSource = null;
+  }
+
+  if (outputAudioContext && outputAudioContext.state !== "closed") {
+    outputAudioContext.close()
+    outputAudioContext = null;
+  }
+
   if (animationFrame) {
     cancelAnimationFrame(animationFrame);
     animationFrame = null;
@@ -654,7 +730,7 @@ function updateUI() {
       statusText.textContent = "Please wait for processing to complete...";
     }
   } else if (isRecording) {
-    statusText.textContent = "Recording...";
+    statusText.textContent = "";
   } else {
     if (
       statusText.textContent !== "Finished processing audio! Ready to record again." &&
@@ -688,3 +764,40 @@ navigator.mediaDevices.addEventListener('devicechange', async () => {
     console.log("Error re-enumerating microphones:", error);
   }
 });
+
+
+settingsToggle.addEventListener("click", () => {
+settingsDiv.classList.toggle("visible");
+settingsToggle.classList.toggle("active");
+});
+
+if (isExtension) {
+  async function checkAndRequestPermissions() {
+    const micPermission = await navigator.permissions.query({
+      name: "microphone",
+    });
+
+    const permissionDisplay = document.getElementById("audioPermission");
+    if (permissionDisplay) {
+      permissionDisplay.innerText = `MICROPHONE: ${micPermission.state}`;
+    }
+
+    // if (micPermission.state !== "granted") {
+    //   chrome.tabs.create({ url: "welcome.html" });
+    // }
+
+    const intervalId = setInterval(async () => {
+      const micPermission = await navigator.permissions.query({
+        name: "microphone",
+      });
+      if (micPermission.state === "granted") {
+        if (permissionDisplay) {
+          permissionDisplay.innerText = `MICROPHONE: ${micPermission.state}`;
+        }
+        clearInterval(intervalId);
+      }
+    }, 100);
+  }
+
+  void checkAndRequestPermissions();
+}

whisperlivekit/web/web_interface.py

@@ -23,6 +23,24 @@ def get_inline_ui_html():
         with resources.files('whisperlivekit.web').joinpath('live_transcription.js').open('r', encoding='utf-8') as f:
             js_content = f.read()
         
+        with resources.files('whisperlivekit.web').joinpath('pcm_worklet.js').open('r', encoding='utf-8') as f:
+            worklet_code = f.read()
+        with resources.files('whisperlivekit.web').joinpath('recorder_worker.js').open('r', encoding='utf-8') as f:
+            worker_code = f.read()
+        
+        js_content = js_content.replace(
+            'await audioContext.audioWorklet.addModule("/web/pcm_worklet.js");',
+            'const workletBlob = new Blob([`' + worklet_code + '`], { type: "application/javascript" });\n' +
+            'const workletUrl = URL.createObjectURL(workletBlob);\n' +
+            'await audioContext.audioWorklet.addModule(workletUrl);'
+        )
+        js_content = js_content.replace(
+            'recorderWorker = new Worker("/web/recorder_worker.js");',
+            'const workerBlob = new Blob([`' + worker_code + '`], { type: "application/javascript" });\n' +
+            'const workerUrl = URL.createObjectURL(workerBlob);\n' +
+            'recorderWorker = new Worker(workerUrl);'
+        )
+        
         # SVG files
         with resources.files('whisperlivekit.web').joinpath('src', 'system_mode.svg').open('r', encoding='utf-8') as f:
             system_svg = f.read()
@@ -33,15 +51,18 @@ def get_inline_ui_html():
         with resources.files('whisperlivekit.web').joinpath('src', 'dark_mode.svg').open('r', encoding='utf-8') as f:
             dark_svg = f.read()
             dark_data_uri = f"data:image/svg+xml;base64,{base64.b64encode(dark_svg.encode('utf-8')).decode('utf-8')}"
-        
+        with resources.files('whisperlivekit.web').joinpath('src', 'settings.svg').open('r', encoding='utf-8') as f:
+            settings = f.read()
+            settings_uri = f"data:image/svg+xml;base64,{base64.b64encode(settings.encode('utf-8')).decode('utf-8')}"
+
         # Replace external references
         html_content = html_content.replace(
-            '<link rel="stylesheet" href="/web/live_transcription.css" />',
+            '<link rel="stylesheet" href="live_transcription.css" />',
             f'<style>\n{css_content}\n</style>'
         )
         
         html_content = html_content.replace(
-            '<script src="/web/live_transcription.js"></script>',
+            '<script src="live_transcription.js"></script>',
             f'<script>\n{js_content}\n</script>'
         )
         
@@ -61,6 +82,11 @@ def get_inline_ui_html():
             f'<img src="{dark_data_uri}" alt="" />'
         )
         
+        html_content = html_content.replace(
+            '<img src="web/src/settings.svg" alt="Settings" />',
+            f'<img src="{settings_uri}" alt="" />'
+        )
+        
         return html_content
         
     except Exception as e:

whisperlivekit/whisper_streaming_custom/backends.py

@@ -11,14 +11,14 @@ class ASRBase:
     sep = " "  # join transcribe words with this character (" " for whisper_timestamped,
               # "" for faster-whisper because it emits the spaces when needed)
 
-    def __init__(self, lan, modelsize=None, cache_dir=None, model_dir=None, logfile=sys.stderr):
+    def __init__(self, lan, model_size=None, cache_dir=None, model_dir=None, logfile=sys.stderr):
         self.logfile = logfile
         self.transcribe_kargs = {}
         if lan == "auto":
             self.original_language = None
         else:
             self.original_language = lan
-        self.model = self.load_model(modelsize, cache_dir, model_dir)
+        self.model = self.load_model(model_size, cache_dir, model_dir)
 
     def with_offset(self, offset: float) -> ASRToken:
         # This method is kept for compatibility (typically you will use ASRToken.with_offset)
@@ -27,7 +27,7 @@ class ASRBase:
     def __repr__(self):
         return f"ASRToken(start={self.start:.2f}, end={self.end:.2f}, text={self.text!r})"
 
-    def load_model(self, modelsize, cache_dir, model_dir):
+    def load_model(self, model_size, cache_dir, model_dir):
         raise NotImplementedError("must be implemented in the child class")
 
     def transcribe(self, audio, init_prompt=""):
@@ -41,7 +41,7 @@ class WhisperTimestampedASR(ASRBase):
     """Uses whisper_timestamped as the backend."""
     sep = " "
 
-    def load_model(self, modelsize=None, cache_dir=None, model_dir=None):
+    def load_model(self, model_size=None, cache_dir=None, model_dir=None):
         import whisper
         import whisper_timestamped
         from whisper_timestamped import transcribe_timestamped
@@ -49,7 +49,7 @@ class WhisperTimestampedASR(ASRBase):
         self.transcribe_timestamped = transcribe_timestamped
         if model_dir is not None:
             logger.debug("ignoring model_dir, not implemented")
-        return whisper.load_model(modelsize, download_root=cache_dir)
+        return whisper.load_model(model_size, download_root=cache_dir)
 
     def transcribe(self, audio, init_prompt=""):
         result = self.transcribe_timestamped(
@@ -88,17 +88,17 @@ class FasterWhisperASR(ASRBase):
     """Uses faster-whisper as the backend."""
     sep = ""
 
-    def load_model(self, modelsize=None, cache_dir=None, model_dir=None):
+    def load_model(self, model_size=None, cache_dir=None, model_dir=None):
         from faster_whisper import WhisperModel
 
         if model_dir is not None:
             logger.debug(f"Loading whisper model from model_dir {model_dir}. "
-                         f"modelsize and cache_dir parameters are not used.")
+                         f"model_size and cache_dir parameters are not used.")
             model_size_or_path = model_dir
-        elif modelsize is not None:
+        elif model_size is not None:
-            model_size_or_path = modelsize
+            model_size_or_path = model_size
         else:
-            raise ValueError("Either modelsize or model_dir must be set")
+            raise ValueError("Either model_size or model_dir must be set")
         device = "auto" # Allow CTranslate2 to decide available device
         compute_type = "auto" # Allow CTranslate2 to decide faster compute type
                               
@@ -149,18 +149,18 @@ class MLXWhisper(ASRBase):
     """
     sep = ""
 
-    def load_model(self, modelsize=None, cache_dir=None, model_dir=None):
+    def load_model(self, model_size=None, cache_dir=None, model_dir=None):
         from mlx_whisper.transcribe import ModelHolder, transcribe
         import mlx.core as mx
 
         if model_dir is not None:
-            logger.debug(f"Loading whisper model from model_dir {model_dir}. modelsize parameter is not used.")
+            logger.debug(f"Loading whisper model from model_dir {model_dir}. model_size parameter is not used.")
             model_size_or_path = model_dir
-        elif modelsize is not None:
+        elif model_size is not None:
-            model_size_or_path = self.translate_model_name(modelsize)
+            model_size_or_path = self.translate_model_name(model_size)
-            logger.debug(f"Loading whisper model {modelsize}. You use mlx whisper, so {model_size_or_path} will be used.")
+            logger.debug(f"Loading whisper model {model_size}. You use mlx whisper, so {model_size_or_path} will be used.")
         else:
-            raise ValueError("Either modelsize or model_dir must be set")
+            raise ValueError("Either model_size or model_dir must be set")
 
         self.model_size_or_path = model_size_or_path
         dtype = mx.float16

whisperlivekit/whisper_streaming_custom/online_asr.py

@@ -106,9 +106,6 @@ class OnlineASRProcessor:
     def __init__(
         self,
         asr,
-        tokenize_method: Optional[callable] = None,
-        buffer_trimming: Tuple[str, float] = ("segment", 15),
-        confidence_validation = False,
         logfile=sys.stderr,
     ):
         """
@@ -119,13 +116,14 @@ class OnlineASRProcessor:
         buffer_trimming: A tuple (option, seconds), where option is either "sentence" or "segment".
         """
         self.asr = asr
-        self.tokenize = tokenize_method
+        self.tokenize = asr.tokenizer
         self.logfile = logfile
-        self.confidence_validation = confidence_validation
+        self.confidence_validation = asr.confidence_validation
         self.global_time_offset = 0.0
         self.init()
 
-        self.buffer_trimming_way, self.buffer_trimming_sec = buffer_trimming
+        self.buffer_trimming_way = asr.buffer_trimming
+        self.buffer_trimming_sec = asr.buffer_trimming_sec
 
         if self.buffer_trimming_way not in ["sentence", "segment"]:
             raise ValueError("buffer_trimming must be either 'sentence' or 'segment'")

whisperlivekit/whisper_streaming_custom/whisper_online.py

@@ -6,6 +6,7 @@ from functools import lru_cache
 import time
 import logging
 from .backends import FasterWhisperASR, MLXWhisper, WhisperTimestampedASR, OpenaiApiASR
+from whisperlivekit.warmup import warmup_asr
 
 logger = logging.getLogger(__name__)
 
@@ -63,11 +64,23 @@ def create_tokenizer(lan):
     return WtPtok()
 
 
-def backend_factory(args):
+def backend_factory(
-    backend = args.backend
+            backend,
+            lan,
+            model_size,
+            model_cache_dir,
+            model_dir,
+            task,
+            buffer_trimming,
+            buffer_trimming_sec,
+            confidence_validation,
+            warmup_file=None,
+            min_chunk_size=None,
+        ):
+    backend = backend
     if backend == "openai-api":
         logger.debug("Using OpenAI API.")
-        asr = OpenaiApiASR(lan=args.lan)        
+        asr = OpenaiApiASR(lan=lan)        
     else:
         if backend == "faster-whisper":
             asr_cls = FasterWhisperASR
@@ -77,34 +90,33 @@ def backend_factory(args):
             asr_cls = WhisperTimestampedASR
 
         # Only for FasterWhisperASR and WhisperTimestampedASR
-        size = args.model
+
         t = time.time()
-        logger.info(f"Loading Whisper {size} model for language {args.lan}...")
+        logger.info(f"Loading Whisper {model_size} model for language {lan}...")
         asr = asr_cls(
-            modelsize=size,
+            model_size=model_size,
-            lan=args.lan,
+            lan=lan,
-            cache_dir=getattr(args, 'model_cache_dir', None),
+            cache_dir=model_cache_dir,
-            model_dir=getattr(args, 'model_dir', None),
+            model_dir=model_dir,
         )
         e = time.time()
         logger.info(f"done. It took {round(e-t,2)} seconds.")
 
-    # Apply common configurations
+    if task == "translate":
-    if getattr(args, "vad", False):  # Checks if VAD argument is present and True
-        logger.info("Setting VAD filter")
-        asr.use_vad()
-
-    language = args.lan
-    if args.task == "translate":
-        if backend != "simulstreaming":
-            asr.set_translate_task()
         tgt_language = "en"  # Whisper translates into English
     else:
-        tgt_language = language  # Whisper transcribes in this language
+        tgt_language = lan  # Whisper transcribes in this language
 
     # Create the tokenizer
-    if args.buffer_trimming == "sentence":
+    if buffer_trimming == "sentence":
         tokenizer = create_tokenizer(tgt_language)
     else:
         tokenizer = None
-    return asr, tokenizer
+    
+    warmup_asr(asr, warmup_file)
+    
+    asr.confidence_validation = confidence_validation
+    asr.tokenizer = tokenizer
+    asr.buffer_trimming = buffer_trimming
+    asr.buffer_trimming_sec = buffer_trimming_sec
+    return asr