{
 "schema_version": 1,
 "generated": "2026-11-09",
 "repo": "modelscope/FunASR",
 "name": "FunASR",
 "owner": "modelscope",
 "slug": "modelscope-funasr",
 "github": "https://github.com/modelscope/FunASR",
 "what": "FunASR is an industrial speech recognition toolkit for offline, streaming and edge deployment. It bundles ASR models such as SenseVoiceSmall, Paraformer and Fun-ASR-Nano with VAD, punctuation, speaker clustering and emotion models, a `funasr` CLI with JSON and SRT output, an OpenAI-compatible `funasr-server`, and llama.cpp GGUF binaries that run on CPU without Python.",
 "why": "21k stars, talked about in 2 AI sources we track",
 "language": "",
 "requirements": [
  "Python >= 3.8 with PyTorch and torchaudio installed first, then `pip install funasr`",
  "A CPU is enough for SenseVoiceSmall; use device cuda only after confirming torch.cuda.is_available() prints True",
  "Python 3.11 plus fastapi, uvicorn and python-multipart for the local HTTP server"
 ],
 "audience_note": "Developers who need transcription beyond Whisper, especially for Chinese and other Asian languages, with speaker labels and subtitles.",
 "risk": "none",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Content",
 "url": "https://dedupedai.com/use-cases/modelscope-funasr/",
 "use_case_count": 3,
 "use_cases": [
  {
   "id": "modelscope-funasr--make-srt-subtitles-from-audio-with-funasr",
   "title": "Make SRT subtitles from audio files",
   "best": true,
   "url": "https://dedupedai.com/use-cases/modelscope-funasr/make-srt-subtitles-from-audio-with-funasr/",
   "json": "https://dedupedai.com/use-cases/u/modelscope-funasr/make-srt-subtitles-from-audio-with-funasr.json"
  },
  {
   "id": "modelscope-funasr--transcribe-meetings-with-speaker-labels-using-funasr",
   "title": "Transcribe a meeting with speaker labels",
   "best": false,
   "url": "https://dedupedai.com/use-cases/modelscope-funasr/transcribe-meetings-with-speaker-labels-using-funasr/",
   "json": "https://dedupedai.com/use-cases/u/modelscope-funasr/transcribe-meetings-with-speaker-labels-using-funasr.json"
  },
  {
   "id": "modelscope-funasr--run-a-local-openai-compatible-transcription-server-with-funa",
   "title": "Run a local OpenAI style transcription API",
   "best": false,
   "url": "https://dedupedai.com/use-cases/modelscope-funasr/run-a-local-openai-compatible-transcription-server-with-funa/",
   "json": "https://dedupedai.com/use-cases/u/modelscope-funasr/run-a-local-openai-compatible-transcription-server-with-funa.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}
