openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.86M • • 5.6k
STT (Speech To Text)
Speech to Text (ASR) - Best Open Source models
-
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 6.6M • • 2.95k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 172k • 1.46k -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 70k • 970 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.76M • 749 -
distil-whisper/distil-large-v3
Automatic Speech Recognition • 0.8B • Updated • 1.2M • 375 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 166k • 374 -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 10.3M • 1.77k -
ibm-granite/granite-4.0-1b-speech
Automatic Speech Recognition • 2B • Updated • 82.2k • 226 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 385k • 791