openai/whisper-large-v3
Automatic Speech Recognition • Updated • 4.67M • • 5.54k
STT (Speech To Text)
Speech to Text (ASR) - Best Open Source models
-
-
openai/whisper-large-v3-turbo
Automatic Speech Recognition • Updated • 5M • • 2.89k -
nvidia/parakeet-tdt-0.6b-v2
Automatic Speech Recognition • Updated • 162k • 1.44k -
facebook/seamless-m4t-v2-large
Automatic Speech Recognition • 2B • Updated • 92.4k • 966 -
Qwen/Qwen3-ASR-1.7B
Automatic Speech Recognition • 2B • Updated • 1.19M • 644 -
distil-whisper/distil-large-v3
Automatic Speech Recognition • Updated • 1.11M • 374 -
nvidia/canary-1b-v2
Automatic Speech Recognition • Updated • 122k • 371 -
pyannote/speaker-diarization-3.1
Automatic Speech Recognition • Updated • 11.2M • 1.71k -
ibm-granite/granite-4.0-1b-speech
Automatic Speech Recognition • 2B • Updated • 62.2k • 211 -
nvidia/parakeet-tdt-0.6b-v3
Automatic Speech Recognition • Updated • 260k • 749