Upload index.js with huggingface_hub

index.js

@@ -1,76 +1,75 @@
-import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/transformers@3.4.1';
-
-// Reference the elements that we will need
+import { pipeline } from '@huggingface/transformers';
+
+// Initialize transcriber (lazy loading)
+let transcriber;
+const getTranscriber = async () => {
+  if (!transcriber) {
+    document.getElementById('status').textContent = 'Loading Whisper model...';
+    transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-tiny.en');
+    document.getElementById('status').textContent = 'Model loaded.';
+  }
+  return transcriber;
+};
+
+// DOM Elements
+const audioInput = document.getElementById('audioInput');
+const useSampleBtn = document.getElementById('useSample');
+const player = document.getElementById('player');
+const output = document.getElementById('output');
 const status = document.getElementById('status');
-const fileUpload = document.getElementById('upload');
-const imageContainer = document.getElementById('container');
-const example = document.getElementById('example');
-
-const EXAMPLE_URL = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/city-streets.jpg';
-
-// Create a new object detection pipeline
-status.textContent = 'Loading model...';
-const detector = await pipeline('object-detection', 'Xenova/detr-resnet-50');
-status.textContent = 'Ready';
-
-example.addEventListener('click', (e) => {
-    e.preventDefault();
-    detect(EXAMPLE_URL);
+const modeOptions = document.querySelectorAll('input[name="mode"]');
+
+// Set audio source from file
+audioInput.addEventListener('change', (e) => {
+  const file = e.target.files[0];
+  if (file) {
+    const url = URL.createObjectURL(file);
+    player.src = url;
+    output.textContent = '';
+  }
 });
 
-fileUpload.addEventListener('change', function (e) {
-    const file = e.target.files[0];
-    if (!file) {
-        return;
-    }
-
-    const reader = new FileReader();
-
-    // Set up a callback when the file is loaded
-    reader.onload = e2 => detect(e2.target.result);
-
-    reader.readAsDataURL(file);
+// Use sample JFK audio
+useSampleBtn.addEventListener('click', () => {
+  const sampleUrl = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
+  player.src = sampleUrl;
+  output.textContent = '';
 });
 
+// Get selected mode
+const getSelectedMode = () => {
+  for (const option of modeOptions) {
+    if (option.checked) return option.value;
+  }
+  return 'normal';
+};
+
+// Transcribe button click handler
+player.addEventListener('play', async () => {
+  try {
+    const transcriber = await getTranscriber();
+    const mode = getSelectedMode();
+
+    // Prepare transcription options
+    let options = {};
+    if (mode === 'chunks') {
+      options.return_timestamps = true;
+    } else if (mode === 'words') {
+      options.return_timestamps = 'word';
+    }
 
-// Detect objects in the image
-async function detect(img) {
-    imageContainer.innerHTML = '';
-    imageContainer.style.backgroundImage = `url(${img})`;
-
-    status.textContent = 'Analysing...';
-    const output = await detector(img, {
-        threshold: 0.5,
-        percentage: true,
-    });
-    status.textContent = '';
-    output.forEach(renderBox);
-}
-
-// Render a bounding box and label on the image
-function renderBox({ box, label }) {
-    const { xmax, xmin, ymax, ymin } = box;
-
-    // Generate a random color for the box
-    const color = '#' + Math.floor(Math.random() * 0xFFFFFF).toString(16).padStart(6, 0);
-
-    // Draw the box
-    const boxElement = document.createElement('div');
-    boxElement.className = 'bounding-box';
-    Object.assign(boxElement.style, {
-        borderColor: color,
-        left: 100 * xmin + '%',
-        top: 100 * ymin + '%',
-        width: 100 * (xmax - xmin) + '%',
-        height: 100 * (ymax - ymin) + '%',
-    })
-
-    // Draw label
-    const labelElement = document.createElement('span');
-    labelElement.textContent = label;
-    labelElement.className = 'bounding-box-label';
-    labelElement.style.backgroundColor = color;
-
-    boxElement.appendChild(labelElement);
-    imageContainer.appendChild(boxElement);
-}
+    // Update status
+    status.textContent = 'Transcribing...';
+    output.textContent = 'Transcribing...';
+
+    // Perform transcription
+    const result = await transcriber(player.src, options);
+    output.textContent = JSON.stringify(result, null, 2);
+
+    status.textContent = 'Transcription complete.';
+  } catch (err) {
+    console.error(err);
+    status.textContent = `Error: ${err.message}`;
+    output.textContent = '';
+  }
+});