Open ASR Leaderboard
🏆
1.39k
Compare speech-to-text models by WER and speed
STT
-
-
nvidia/canary-qwen-2.5b
Automatic Speech Recognition • 3B • Updated • 111k • 441 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 157k • • 950 -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 393k • 1.51k -
stabilityai/stable-video-diffusion-img2vid
Image-to-Video • Updated • 32.4k • 1.04k -
LiquidAI/LFM2-Audio-1.5B
Audio-to-Audio • 1B • Updated • 337 • 350 -
mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 1.87M • 895