Spaces:

AtPeak
/

realtime-stt-translation

Paused

File size: 8,842 Bytes

<!DOCTYPE html>
<html lang="en">
<head>
  <meta charset="UTF-8"/>
  <meta name="viewport" content="width=device-width, initial-scale=1.0"/>
  <title>Audio Transcription</title>
  <style>
    body {
      font-family: 'Inter', sans-serif;
      margin: 20px;
      text-align: center;
    }
    #recordButton {
      width: 80px;
      height: 80px;
      font-size: 36px;
      border: none;
      border-radius: 50%;
      background-color: white;
      cursor: pointer;
      box-shadow: 0 0px 10px rgba(0, 0, 0, 0.2);
      transition: background-color 0.3s ease, transform 0.2s ease;
    }
    #recordButton.recording {
      background-color: #ff4d4d;
      color: white;
    }
    #recordButton:active {
      transform: scale(0.95);
    }
    #status {
      margin-top: 20px;
      font-size: 16px;
      color: #333;
    }
    .settings-container {
      display: flex;
      justify-content: center;
      align-items: center;
      gap: 15px;
      margin-top: 20px;
    }
    .settings {
      display: flex;
      flex-direction: column;
      align-items: flex-start;
      gap: 5px;
    }
    #chunkSelector,
    #websocketInput {
      font-size: 16px;
      padding: 5px;
      border-radius: 5px;
      border: 1px solid #ddd;
      background-color: #f9f9f9;
    }
    #websocketInput {
      width: 200px;
    }
    #chunkSelector:focus,
    #websocketInput:focus {
      outline: none;
      border-color: #007bff;
    }
    label {
      font-size: 14px;
    }
    /* Speaker-labeled transcript area */
    #linesTranscript {
      margin: 20px auto;
      max-width: 600px;
      text-align: left;
      font-size: 16px;
    }
    #linesTranscript p {
      margin: 5px 0;
    }
    #linesTranscript strong {
      color: #333;
    }
    /* Grey buffer styling */
    .buffer {
      color: rgb(180, 180, 180);
      font-style: italic;
      margin-left: 4px;
    }
  </style>
</head>
<body>

  <div class="settings-container">
    <button id="recordButton">🎙️</button>
    <div class="settings">
      <div>
        <label for="chunkSelector">Chunk size (ms):</label>
        <select id="chunkSelector">
          <option value="500" selected>500 ms</option>
          <option value="1000">1000 ms</option>
          <option value="2000">2000 ms</option>
          <option value="3000">3000 ms</option>
          <option value="4000">4000 ms</option>
          <option value="5000">5000 ms</option>
        </select>
      </div>
      <div>
        <label for="websocketInput">WebSocket URL:</label>
        <input id="websocketInput" type="text" value="wss://atpeak-realtime-stt-translation.hf.space/asr" />
      </div>
    </div>
  </div>

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

  <!-- Speaker-labeled transcript -->
  <div id="linesTranscript"></div>

  <script>
    let isRecording = false;
    let websocket = null;
    let recorder = null;
    let chunkDuration = 500;
    let websocketUrl = "ws://localhost:8000/asr";
    let userClosing = false;
    let lines = []; // フロント側でlinesを保持
    let audioQueue = []; // 再生待ちのaudio_urlを保持
    let isPlayingAudio = false; // オーディオ再生中かどうかを示すフラグ
    let currentAudio = null; // 現在再生中のオーディオを保持

    const statusText = document.getElementById("status");
    const recordButton = document.getElementById("recordButton");
    const chunkSelector = document.getElementById("chunkSelector");
    const websocketInput = document.getElementById("websocketInput");
    const linesTranscriptDiv = document.getElementById("linesTranscript");

    chunkSelector.addEventListener("change", () => {
      chunkDuration = parseInt(chunkSelector.value);
    });

    websocketInput.addEventListener("change", () => {
      const urlValue = websocketInput.value.trim();
      if (!urlValue.startsWith("ws://") && !urlValue.startsWith("wss://")) {
        statusText.textContent = "Invalid WebSocket URL (must start with ws:// or wss://)";
        return;
      }
      websocketUrl = urlValue;
      statusText.textContent = "WebSocket URL updated. Ready to connect.";
    });

    function setupWebSocket() {
      return new Promise((resolve, reject) => {
        try {
          websocket = new WebSocket(websocketUrl);
        } catch (error) {
          statusText.textContent = "Invalid WebSocket URL. Please check and try again.";
          reject(error);
          return;
        }

        websocket.onopen = () => {
          statusText.textContent = "Connected to server.";
          resolve();
        };

        websocket.onclose = () => {
          if (userClosing) {
            statusText.textContent = "WebSocket closed by user.";
          } else {
            statusText.textContent =
              "Disconnected from the WebSocket server. (Check logs if model is loading.)";
          }
          userClosing = false;
        };

        websocket.onerror = () => {
          statusText.textContent = "Error connecting to WebSocket.";
          reject(new Error("Error connecting to WebSocket"));
        };

        // Handle messages from server
        websocket.onmessage = (event) => {
          const data = JSON.parse(event.data);
          /*
            The server might send:
            {
              "line": {"speaker": 0, "text": "Hello."},
              "buffer": "...",
              "audio_url": "https://example.com/audio.wav"
            }
          */
          const { line = "", buffer = "" } = data;
          if (line) {
            lines.push(line); // 新しいlineをスタック
            renderLinesWithBuffer(lines, buffer);
          }
          if (line.audio_url) {
            audioQueue.push(line.audio_url);
            if (!isPlayingAudio) {
              playNextAudio();
            }
          }
        };
      });
    }

    function renderLinesWithBuffer(lines, buffer) {
      // Build the HTML
      // The buffer is appended to the last line if it's non-empty
      const linesHtml = lines.map((item, idx) => {
        let textContent = item.text;
        if (idx === lines.length - 1 && buffer) {
          textContent += `<span class="buffer">${buffer}</span>`;
        }
        return `<p><strong>Speaker ${item.speaker}:</strong> ${textContent}</p>`;
      }).join("");

      linesTranscriptDiv.innerHTML = linesHtml;
    }

    function playNextAudio() {
      if (audioQueue.length === 0) {
        isPlayingAudio = false;
        return;
      }
      isPlayingAudio = true;
      const url = audioQueue.shift(); // ここでshiftして次のオーディオを取得
      currentAudio = new Audio(url);
      currentAudio.onended = () => {
        playNextAudio(); // 再生が終了したときに次のオーディオを再生
      };
      currentAudio.onerror = (err) => {
        console.error("Error playing audio:", err);
        playNextAudio(); // エラーが発生した場合も次のオーディオを再生
      };
      currentAudio.play().catch(err => {
        console.error("Error playing audio:", err);
        playNextAudio(); // 再生エラーが発生した場合も次のオーディオを再生
      });
    }

    async function startRecording() {
      try {
        const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
        recorder = new MediaRecorder(stream, { mimeType: "audio/webm" });
        recorder.ondataavailable = (e) => {
          if (websocket && websocket.readyState === WebSocket.OPEN) {
            websocket.send(e.data);
          }
        };
        recorder.start(chunkDuration);
        isRecording = true;
        updateUI();
      } catch (err) {
        statusText.textContent = "Error accessing microphone. Please allow microphone access.";
      }
    }

    function stopRecording() {
      userClosing = true;
      if (recorder) {
        recorder.stop();
        recorder = null;
      }
      isRecording = false;

      if (websocket) {
        websocket.close();
        websocket = null;
      }

      if (currentAudio) {
        currentAudio.pause();
        currentAudio = null;
      }

      updateUI();
    }

    async function toggleRecording() {
      if (!isRecording) {
        linesTranscriptDiv.innerHTML = "";
        lines = []; // 録音開始時にlinesをクリア
        try {
          await setupWebSocket();
          await startRecording();
        } catch (err) {
          statusText.textContent = "Could not connect to WebSocket or access mic. Aborted.";
        }
      } else {
        stopRecording();
      }
    }

    function updateUI() {
      recordButton.classList.toggle("recording", isRecording);
      statusText.textContent = isRecording ? "Recording..." : "Click to start transcription";
    }

    recordButton.addEventListener("click", toggleRecording);
  </script>
</body>
</html>