Spaces:
Running
Running
File size: 17,213 Bytes
c836ca5 e791eef c836ca5 f01c9d3 7e27968 01570e1 e791eef c836ca5 01570e1 e791eef c836ca5 f01c9d3 c836ca5 77b219c c836ca5 f01c9d3 c836ca5 01570e1 e791eef 01570e1 e791eef 77b219c e791eef 77b219c e791eef c836ca5 e9a623f e791eef e9a623f e791eef e9a623f e791eef c836ca5 f01c9d3 c836ca5 f01c9d3 c836ca5 f01c9d3 e791eef 01570e1 c836ca5 01570e1 e791eef 01570e1 e791eef 01570e1 7e27968 c836ca5 f01c9d3 c836ca5 ec858b7 c836ca5 ec858b7 c836ca5 f01c9d3 c836ca5 ec858b7 f01c9d3 ec858b7 f01c9d3 c836ca5 ec858b7 c836ca5 ec858b7 c836ca5 a2409a8 7e27968 01570e1 e9a623f 01570e1 e791eef 01570e1 c836ca5 f01c9d3 c836ca5 f01c9d3 c836ca5 01570e1 c836ca5 01570e1 a2409a8 01570e1 a2409a8 01570e1 7e27968 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 | import { useState, useRef, useEffect } from 'react'
import CLAPProcessor from './clapProcessor'
import UserFeedbackStore from './userFeedbackStore'
import LocalClassifier from './localClassifier'
import './App.css'
function App() {
const [audioFile, setAudioFile] = useState(null)
const [isRecording, setIsRecording] = useState(false)
const [isLoading, setIsLoading] = useState(false)
const [tags, setTags] = useState([])
const [error, setError] = useState(null)
const [customTags, setCustomTags] = useState([])
const [newTag, setNewTag] = useState('')
const [audioHash, setAudioHash] = useState(null)
const [audioFeatures, setAudioFeatures] = useState(null)
const fileInputRef = useRef(null)
const mediaRecorderRef = useRef(null)
const chunksRef = useRef([])
const clapProcessorRef = useRef(null)
const feedbackStoreRef = useRef(null)
const localClassifierRef = useRef(null)
useEffect(() => {
const initializeStore = async () => {
// Initialize CLAP processor once and reuse
clapProcessorRef.current = new CLAPProcessor()
feedbackStoreRef.current = new UserFeedbackStore()
await feedbackStoreRef.current.initialize()
localClassifierRef.current = new LocalClassifier()
localClassifierRef.current.loadModel()
loadCustomTags()
}
initializeStore()
}, [])
const loadCustomTags = async () => {
try {
const stored = await feedbackStoreRef.current.getCustomTags()
setCustomTags(stored.map(item => item.tag))
} catch (error) {
console.error('Error loading custom tags:', error)
}
}
const handleFileUpload = (event) => {
const file = event.target.files[0]
if (file && file.type.startsWith('audio/')) {
setAudioFile(file)
processAudio(file)
}
}
const handleDrop = (event) => {
event.preventDefault()
const file = event.dataTransfer.files[0]
if (file && file.type.startsWith('audio/')) {
setAudioFile(file)
processAudio(file)
}
}
const handleDragOver = (event) => {
event.preventDefault()
}
const startRecording = async () => {
try {
const stream = await navigator.mediaDevices.getUserMedia({ audio: true })
mediaRecorderRef.current = new MediaRecorder(stream)
chunksRef.current = []
mediaRecorderRef.current.ondataavailable = (event) => {
chunksRef.current.push(event.data)
}
mediaRecorderRef.current.onstop = () => {
const blob = new Blob(chunksRef.current, { type: 'audio/wav' })
const file = new File([blob], 'recording.wav', { type: 'audio/wav' })
setAudioFile(file)
processAudio(file)
stream.getTracks().forEach(track => track.stop())
}
mediaRecorderRef.current.start()
setIsRecording(true)
} catch (error) {
console.error('Error accessing microphone:', error)
}
}
const stopRecording = () => {
if (mediaRecorderRef.current && isRecording) {
mediaRecorderRef.current.stop()
setIsRecording(false)
}
}
const processAudio = async (file) => {
setIsLoading(true)
setTags([])
setError(null)
try {
// CLAP processor should already be initialized in useEffect
if (!clapProcessorRef.current) {
console.warn('CLAP processor not initialized, creating new instance')
clapProcessorRef.current = new CLAPProcessor()
}
const hash = await feedbackStoreRef.current.hashAudioFile(file)
setAudioHash(hash)
console.log('Converting file to audio buffer...')
const audioBuffer = await clapProcessorRef.current.fileToAudioBuffer(file)
console.log('Audio buffer created:', {
duration: audioBuffer.duration,
sampleRate: audioBuffer.sampleRate,
channels: audioBuffer.numberOfChannels
})
console.log('Processing audio with CLAP...')
const generatedTags = await clapProcessorRef.current.processAudio(audioBuffer)
console.log('Generated tags:', generatedTags)
// Store basic audio info for later use
const features = {
sampleRate: audioBuffer.sampleRate,
duration: audioBuffer.duration,
numberOfChannels: audioBuffer.numberOfChannels
}
setAudioFeatures(features)
// Apply local classifier adjustments
let finalTags = generatedTags.map(tag => ({ ...tag, userFeedback: null }))
if (localClassifierRef.current) {
const simpleFeatures = localClassifierRef.current.extractSimpleFeatures(features)
const allPossibleTags = [...generatedTags.map(t => t.label), ...customTags]
const localPredictions = localClassifierRef.current.predictAll(simpleFeatures, allPossibleTags)
// Merge CLAP predictions with local classifier predictions
const mergedTags = new Map()
// Add CLAP tags
for (const tag of generatedTags) {
mergedTags.set(tag.label, { ...tag, source: 'clap' })
}
// Add or adjust with local predictions
for (const pred of localPredictions) {
if (mergedTags.has(pred.tag)) {
// Blend CLAP and local predictions
const existing = mergedTags.get(pred.tag)
existing.confidence = (existing.confidence + pred.confidence) / 2
existing.source = 'blended'
} else if (pred.confidence > 0.6) {
// Add high-confidence local predictions
mergedTags.set(pred.tag, {
label: pred.tag,
confidence: pred.confidence,
source: 'local',
userFeedback: null
})
}
}
finalTags = Array.from(mergedTags.values())
.sort((a, b) => b.confidence - a.confidence)
.slice(0, 8) // Keep top 8 tags
}
setTags(finalTags)
} catch (err) {
console.error('Error processing audio:', err)
setError('Failed to process audio. Using fallback tags.')
// Fallback tags
setTags([
{ label: 'audio', confidence: 0.9, userFeedback: null },
{ label: 'sound', confidence: 0.8, userFeedback: null },
{ label: 'recording', confidence: 0.7, userFeedback: null }
])
} finally {
setIsLoading(false)
}
}
const handleTagFeedback = async (tagIndex, feedback) => {
const updatedTags = [...tags]
updatedTags[tagIndex].userFeedback = feedback
setTags(updatedTags)
try {
await feedbackStoreRef.current.saveTagFeedback(
updatedTags[tagIndex].label,
feedback,
audioHash
)
// Train local classifier on this feedback
if (localClassifierRef.current && audioFeatures) {
const simpleFeatures = localClassifierRef.current.extractSimpleFeatures(audioFeatures)
localClassifierRef.current.trainOnFeedback(
simpleFeatures,
updatedTags[tagIndex].label,
feedback
)
localClassifierRef.current.saveModel()
}
} catch (error) {
console.error('Error saving tag feedback:', error)
}
}
const handleAddCustomTag = async () => {
const trimmedTag = newTag.trim().toLowerCase()
// Validation
if (!trimmedTag) {
setError('Please enter a tag name')
return
}
if (trimmedTag.length < 2) {
setError('Tag must be at least 2 characters long')
return
}
// Check if tag already exists
const existingTag = tags.find(tag => tag.label.toLowerCase() === trimmedTag)
if (existingTag) {
setError(`Tag "${trimmedTag}" already exists`)
return
}
// Clear any previous errors
setError(null)
const customTag = {
label: trimmedTag,
confidence: 1.0,
userFeedback: 'custom',
isCustom: true,
source: 'custom'
}
setTags(prev => [...prev, customTag])
try {
if (feedbackStoreRef.current) {
await feedbackStoreRef.current.saveCustomTag(trimmedTag)
if (audioHash) {
await feedbackStoreRef.current.saveTagFeedback(trimmedTag, 'custom', audioHash)
}
}
// Train local classifier on custom tag
if (localClassifierRef.current && audioFeatures) {
const simpleFeatures = localClassifierRef.current.extractSimpleFeatures(audioFeatures)
localClassifierRef.current.trainOnFeedback(
simpleFeatures,
trimmedTag,
'custom'
)
localClassifierRef.current.saveModel()
}
loadCustomTags()
console.log(`β
Added custom tag: "${trimmedTag}"`)
} catch (error) {
console.error('Error saving custom tag:', error)
setError('Failed to save custom tag')
}
setNewTag('')
}
const handleKeyPress = (e) => {
if (e.key === 'Enter') {
handleAddCustomTag()
}
}
const exportModel = async () => {
try {
const modelStats = localClassifierRef.current?.getModelStats()
const feedbackData = await feedbackStoreRef.current.getAudioFeedback()
const customTagsData = await feedbackStoreRef.current.getCustomTags()
const exportData = {
modelStats,
feedbackData: feedbackData.slice(0, 50), // Limit for size
customTags: customTagsData,
exportDate: new Date().toISOString(),
version: '1.0'
}
const blob = new Blob([JSON.stringify(exportData, null, 2)], {
type: 'application/json'
})
const url = URL.createObjectURL(blob)
const a = document.createElement('a')
a.href = url
a.download = `clip-tagger-model-${Date.now()}.json`
document.body.appendChild(a)
a.click()
document.body.removeChild(a)
URL.revokeObjectURL(url)
} catch (error) {
console.error('Error exporting model:', error)
setError('Failed to export model')
}
}
const exportTags = () => {
if (tags.length === 0) return
const tagData = {
audioFile: audioFile?.name || 'recorded-audio',
audioHash,
timestamp: new Date().toISOString(),
tags: tags.map(tag => ({
label: tag.label,
confidence: tag.confidence,
source: tag.source || 'clap',
userFeedback: tag.userFeedback
}))
}
const blob = new Blob([JSON.stringify(tagData, null, 2)], {
type: 'application/json'
})
const url = URL.createObjectURL(blob)
const a = document.createElement('a')
a.href = url
a.download = `tags-${audioFile?.name || 'audio'}-${Date.now()}.json`
document.body.appendChild(a)
a.click()
document.body.removeChild(a)
URL.revokeObjectURL(url)
}
const clearAllData = async () => {
if (confirm('Are you sure you want to clear all training data? This cannot be undone.')) {
try {
await feedbackStoreRef.current.clearAllData()
localClassifierRef.current?.clearModel()
setCustomTags([])
setTags([])
setAudioFile(null)
setError(null)
} catch (error) {
console.error('Error clearing data:', error)
setError('Failed to clear data')
}
}
}
return (
<div className="app">
<header>
<h1>π΅ clip-tagger</h1>
<p>Custom audio tagging in the browser</p>
</header>
<main>
<div
className="upload-area"
onDrop={handleDrop}
onDragOver={handleDragOver}
onClick={() => fileInputRef.current?.click()}
>
<input
ref={fileInputRef}
type="file"
accept="audio/*"
onChange={handleFileUpload}
hidden
/>
<div className="upload-content">
{audioFile ? (
<div>
<p>π {audioFile.name}</p>
<audio controls src={URL.createObjectURL(audioFile)} />
</div>
) : (
<div>
<p>π΅ Drop an audio file here or click to upload</p>
<p>Supports WAV, MP3, and other audio formats</p>
</div>
)}
</div>
</div>
<div className="controls">
<button
onClick={isRecording ? stopRecording : startRecording}
className={isRecording ? 'recording' : ''}
>
{isRecording ? 'βΉοΈ Stop Recording' : 'π€ Record Audio'}
</button>
</div>
{isLoading && (
<div className="loading">
<p>π§ Analyzing audio with CLAP model...</p>
<p style={{fontSize: '0.9em', opacity: 0.8}}>
{tags.length === 0 ? 'Loading model (~45MB)...' : 'Processing audio...'}
</p>
</div>
)}
{error && (
<div className="error">
<p>β οΈ {error}</p>
</div>
)}
{tags.length > 0 && (
<div className="tags-section">
<h3>Generated Tags</h3>
<div className="tags">
{tags.map((tag, index) => (
<div key={index} className={`tag-item ${tag.userFeedback ? 'has-feedback' : ''}`}>
<span className={`tag ${tag.isCustom ? 'custom' : ''} ${tag.userFeedback === 'negative' ? 'negative' : ''} ${tag.source || 'clap'}`}>
{tag.label} ({Math.round(tag.confidence * 100)}%)
{tag.source === 'local' && <span className="source-indicator">π§ </span>}
{tag.source === 'blended' && <span className="source-indicator">β‘</span>}
{tag.source === 'custom' && <span className="source-indicator">β¨</span>}
</span>
{!tag.isCustom && (
<div className="tag-controls">
<button
onClick={() => handleTagFeedback(index, 'positive')}
className={`feedback-btn ${tag.userFeedback === 'positive' ? 'active' : ''}`}
title="Good tag"
>
β
</button>
<button
onClick={() => handleTagFeedback(index, 'negative')}
className={`feedback-btn ${tag.userFeedback === 'negative' ? 'active' : ''}`}
title="Bad tag"
>
β
</button>
</div>
)}
</div>
))}
</div>
<div className="add-tag">
<input
type="text"
value={newTag}
onChange={(e) => setNewTag(e.target.value)}
onKeyPress={handleKeyPress}
placeholder="Add custom tag..."
className="tag-input"
/>
<button onClick={handleAddCustomTag} className="add-tag-btn">
Add Tag
</button>
</div>
{customTags.length > 0 && (
<div className="frequent-tags">
<h4>Frequent Tags:</h4>
<div className="frequent-tag-list">
{customTags.slice(0, 10).map((tag, index) => (
<button
key={index}
onClick={() => setNewTag(tag)}
className="frequent-tag"
>
{tag}
</button>
))}
</div>
</div>
)}
</div>
)}
{(tags.length > 0 || customTags.length > 0) && (
<div className="export-section">
<h3>Export & Management</h3>
<div className="export-controls">
{tags.length > 0 && (
<button onClick={exportTags} className="export-btn">
π Export Current Tags
</button>
)}
{localClassifierRef.current?.getModelStats().trainedTags > 0 && (
<button onClick={exportModel} className="export-btn">
π§ Export Trained Model
</button>
)}
<button onClick={clearAllData} className="clear-btn">
ποΈ Clear All Data
</button>
</div>
{localClassifierRef.current && (
<div className="model-stats">
<p>Trained tags: {localClassifierRef.current.getModelStats().trainedTags}</p>
<p>Custom tags: {customTags.length}</p>
</div>
)}
</div>
)}
</main>
<footer>
<p>
Powered by <a href="https://github.com/xenova/transformers.js" target="_blank" rel="noopener">Transformers.js</a>
{' '} β’ CLAP model: <a href="https://huggingface.co/Xenova/clap-htsat-unfused" target="_blank" rel="noopener">Xenova/clap-htsat-unfused</a>
{' '} β’ Everything runs locally in your browser
</p>
</footer>
</div>
)
}
export default App
|