modelscope/FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

62
/ 100
Established

FunASR is a versatile toolkit for anyone needing to convert spoken audio into text efficiently and accurately. It takes audio recordings (like speech, interviews, or calls) and outputs precise text transcripts, complete with features like identifying who is speaking, detecting silent parts, and restoring punctuation. This is ideal for professionals like transcriptionists, content creators, or data analysts who work with large volumes of audio.

15,283 stars. Actively maintained with 1 commit in the last 30 days.

Use this if you need to reliably convert diverse audio inputs into clear, structured text, especially for tasks requiring fine-grained control over transcription and speaker identification.

Not ideal if you're a casual user needing basic, one-off audio-to-text conversion without needing advanced features or customization.

audio-transcription voice-to-text meeting-minutes call-center-analysis media-monitoring
No Package No Dependents
Maintenance 16 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

15,283

Forks

1,605

Language

Python

License

MIT

Last pushed

Mar 17, 2026

Commits (30d)

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/modelscope/FunASR"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.