FunAudioLLM

funaudiollm/sensevoice

steady

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

C View on GitHub

Stars

8,699

Forks

786

Open issues

2

24h

+6

+0.1%

7d

+79

+0.9%

Refresh

2h

Star history (7 days)

Last checked

6h ago

Last pushed

5d ago

Next check

4h ago