What do you want to do?
3 use cases
-
Make SRT subtitles from audio files
Use the agent friendly funasr CLI to transcribe one file or a whole batch straight to SRT subtitle files.
View prompt
Using modelscope/FunASR, install it on CPU and run `funasr *.wav --output-format srt --output-dir ./output` in <my audio folder>, then show me the first subtitle file.
-
Transcribe a meeting with speaker labels
Combine ASR with FSMN-VAD and CAM++ speaker clustering to get timestamped segments tagged by anonymous speaker.
View prompt
With modelscope/FunASR, run `funasr audio.wav --spk --timestamps -f json` on <my meeting recording> and turn the JSON into a readable transcript grouped by speaker.
-
Run a local OpenAI style transcription API
Start funasr-server on loopback with SenseVoice on CPU and call it like the OpenAI audio transcriptions endpoint.
View prompt
Using modelscope/FunASR, set up the Python 3.11 venv, start `funasr-server --host 127.0.0.1 --port 8000 --model sensevoice --device cpu`, and send <my wav file> to /v1/audio/transcriptions with curl.
Quick start with FunASR
- Check you have what it needs: 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.
- Open modelscope/FunASR on GitHub and read the README and license.
- Install with
pip install torch torchaudioand thenpip install funasr - Transcribe one file with
funasr audio.wavto check the output - Write subtitles with
funasr audio.wav --output-format srt --output-dir ./subs - Batch a folder with
funasr *.wav --output-format srt --output-dir ./output
These steps come from our top use case, Make SRT subtitles from audio files, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for modelscope/FunASR
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers who need transcription beyond Whisper, especially for Chinese and other Asian languages, with speaker labels and subtitles.
- Why it is hot21k stars, talked about in 2 AI sources we track
- Sourcegithub.com/modelscope/FunASR ยท Back to Hot repos
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
Add this badge to your README
Maintain FunASR? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/modelscope-funasr/?utm_source=github&utm_medium=badge&utm_campaign=modelscope-FunASR)
HTML
<a href="https://dedupedai.com/use-cases/modelscope-funasr/?utm_source=github&utm_medium=badge&utm_campaign=modelscope-FunASR"><img src="https://dedupedai.com/badge/modelscope/FunASR.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about FunASR
What is FunASR?
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. It is an open-source project on GitHub: https://github.com/modelscope/FunASR.
How do I use FunASR?
Install with pip install torch torchaudio and then pip install funasr; then Transcribe one file with funasr audio.wav to check the output; write subtitles with funasr audio.wav --output-format srt --output-dir ./subs. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is FunASR for?
Developers who need transcription beyond Whisper, especially for Chinese and other Asian languages, with speaker labels and subtitles.
What can I do with FunASR?
3 use cases so far, for example: Make SRT subtitles from audio files; Transcribe a meeting with speaker labels; Run a local OpenAI style transcription API. Each has steps and a copy-paste agent prompt.
What do I need to run FunASR?
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.
What are alternatives to FunASR?
Other hot AI repos in Content: Impeccable, Hallmark, OpenMontage, Prompts Chat, Marketingskills.
Is FunASR safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.