2.01k
Whisper
📉
Transcribe audio from microphone, file, or YouTube link
Whisper Release
Whisper includes both English-only and multilingual checkpoints for ASR and ST, ranging from 38M params for the tiny models to 1.5B params for large.
-
-
Robust Speech Recognition via Large-Scale Weak Supervision
Paper • 2212.04356 • Published • 26 -
openai/whisper-large-v2
Automatic Speech Recognition • Updated • 1.31M • 1.68k -
openai/whisper-large
Automatic Speech Recognition • Updated • 1.27M • 491 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 550k • 229 -
openai/whisper-medium.en
Automatic Speech Recognition • Updated • 227k • 50 -
openai/whisper-small
Automatic Speech Recognition • Updated • 12.3M • 350 -
openai/whisper-small.en
Automatic Speech Recognition • Updated • 211k • • 44 -
openai/whisper-base
Automatic Speech Recognition • Updated • 7.13M • 203 -
openai/whisper-base.en
Automatic Speech Recognition • Updated • 2.1M • 31 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 502k • 282 -
openai/whisper-tiny.en
Automatic Speech Recognition • Updated • 166k • 99