Whisper
📉
2.71k
Transcribe audio or YouTube video to text
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 • 51 -
openai/whisper-large-v2
Automatic Speech Recognition • Updated • 79k • 1.78k -
openai/whisper-large
Automatic Speech Recognition • Updated • 85.5k • 532 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 448k • 278 -
openai/whisper-medium.en
Automatic Speech Recognition • 0.8B • Updated • 45.1k • 57 -
openai/whisper-small
Automatic Speech Recognition • Updated • 2.41M • 524 -
openai/whisper-small.en
Automatic Speech Recognition • 0.2B • Updated • 87.9k • 55 -
openai/whisper-base
Automatic Speech Recognition • Updated • 921k • 256 -
openai/whisper-base.en
Automatic Speech Recognition • 72.6M • Updated • 29.3k • 40 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 615k • 413 -
openai/whisper-tiny.en
Automatic Speech Recognition • Updated • 87.1k • 111