Open ASR Leaderboard
🏆
1.42k
Compare speech-to-text models across languages and datasets
STT
-
-
nvidia/canary-qwen-2.5b
Automatic Speech Recognition • 3B • Updated • 45.7k • 451 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 259k • • 1.03k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 719k • 1.53k -
stabilityai/stable-video-diffusion-img2vid
Image-to-Video • 2B • Updated • 24k • 1.05k -
LiquidAI/LFM2-Audio-1.5B
Audio-to-Audio • 1B • Updated • 272 • 361 -
mistralai/Voxtral-Mini-4B-Realtime-2602
Automatic Speech Recognition • 4B • Updated • 2.27M • 936