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

Built on non-autoregressive architectures like Paraformer, FunASR combines ASR with complementary tasks—VAD, punctuation restoration, speaker diarization, and emotion recognition—within a unified framework. The toolkit integrates with ModelScope and Hugging Face for model distribution, and provides production-ready runtime services with optimized CPU/GPU inference pipelines supporting both offline batch processing and low-latency streaming transcription across 31+ languages.

15,283 stars. Actively maintained with 2 commits in the last 30 days.

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)

2

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.