QwenAudio

qwenaudio/sensevoice

steady

Open-source SenseVoiceSmall model for Mandarin, Cantonese, English, Japanese, and Korean ASR, language ID, emotion recognition, and audio event detection.

C View on GitHub

Stars

9,385

Forks

829

Open issues

7

24h

+7

+0.1%

7d

+65

+0.7%

Refresh

1h

Star history (7 days)

Last checked

58m ago

Last pushed

3d ago

Next check

just now