{
  "schemaVersion": "1.0",
  "updates": [],
  "companyNews": [],
  "id": "b884",
  "language": "en",
  "name": "WhisperX",
  "originalName": "WhisperX",
  "library": "tools",
  "category": "Speech recognition & input",
  "categoryKey": "语音识别与输入",
  "categoryKeys": [
    "语音识别与输入"
  ],
  "categories": [
    "Speech recognition & input"
  ],
  "entryPoints": [],
  "summary": "Combine batched ASR, phoneme forced alignment and speaker diarization to create transcripts with word timestamps and anonymous speaker labels.",
  "introduction": "WhisperX chains faster-whisper transcription, VAD segmentation, language-specific phoneme alignment and pyannote diarization for word timelines, subtitles and speaker-labeled transcripts. Recognition, alignment and diarization are separate stages. The current pyannote model requires accepting its terms and providing a Hugging Face token. Overlapping speech, out-of-dictionary words and numbers may not align accurately; speaker labels do not identify real names.",
  "capabilities": [],
  "company": {
    "name": "WhisperX",
    "originalName": "WhisperX"
  },
  "officialUrl": "https://github.com/m-bain/whisperX",
  "profileUpdatedOn": "2026-10-22",
  "sources": [
    {
      "kind": "product",
      "url": "https://github.com/m-bain/whisperX"
    }
  ],
  "news": [],
  "links": {
    "interactive": "products/whisperx--b884.html",
    "reading": "read/en/products/whisperx--b884.html",
    "markdown": "read/en/products/whisperx--b884.md",
    "json": "read/en/products/whisperx--b884.json"
  }
}