openai/whisper-large-v3
Automatic Speech Recognition • 2B • Updated • 4.87M • • 5.62k
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 • • 2.97k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 170k • 1.47k -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 74.9k • 972 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.8M • 762 -
distil-whisper/distil-large-v3
Automatic Speech Recognition • 0.8B • Updated • 1.17M • 376 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 168k • 377 -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 10.3M • 1.79k -
ibm-granite/granite-4.0-1b-speech
Automatic Speech Recognition • 2B • Updated • 92.4k • 231 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • 0.6B • Updated • 398k • 805