GitHubPyPI
FunASR
#28 of 51 in the AI Agent Index ↓ Download poster
51 Score
Observed adoptionCurrent · 2026-09-12 51
MomentumCurrent · 2026-09-12 53
AttentionCurrent · 2026-09-12 49
Signal confidence Based on how many independent score dimensions currently have data.
High3/3 · 2 source types
About
Industrial speech recognition. 170x faster than Whisper. 50+ languages.
No local setup? Open the Colab quickstart to transcribe a public sample or upload your own audio in a browser.
Flagship model — Fun-ASR-Nano (LLM-ASR, 31 languages; the default recommendation, needs a GPU):
On CPU (or for multilingual + emotion in one pass), use SenseVoice — which also returns speaker diarization and timestamps:
Output — structured text with speaker labels, timestamps, and punctuation:
That's it. One model, one call — VAD segmentation, speech recognition, punctuation, speaker diarization all happen automatically.
At scale, accelerate Fun-ASR-Nano with vLLM (batch processing):
Deploy as API…
Across sources
355.6k Downloads / month
- Downloads / month 355.6k
- Downloads / week 58.7k
- Downloads / day 9.5k
20.3k Stars
- Stars 20.3k
- Forks 2.0k
- Commits 5.9k
- Releases 64