openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.91M • • 5.67k
STT (Speech To Text)
Speech to Text (ASR) - Best Open Source models
-
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition • 0.8B • Updated • 6.88M • • 3k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 159k • 1.47k -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 84.4k • 977 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 2.02M • 793 -
distil-whisper/distil-large-v3
Automatic Speech Recognition • 0.8B • Updated • 1.3M • 376 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 118k • 380 -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 10.2M • 1.85k -
ibm-granite/granite-4.0-1b-speech
Automatic Speech Recognition • 2B • Updated • 123k • 240 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 416k • 831