Whisper
📉
2.76k
Transcribe audio files into 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 • 53 -
openai/whisper-large-v2
Automatic Speech Recognition • Updated • 72.9k • 1.79k -
openai/whisper-large
Automatic Speech Recognition • Updated • 40.3k • 541 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 576k • 283 -
openai/whisper-medium.en
Automatic Speech Recognition • 0.8B • Updated • 37.4k • 57 -
openai/whisper-small
Automatic Speech Recognition • Updated • 1.81M • 546 -
openai/whisper-small.en
Automatic Speech Recognition • 0.2B • Updated • 75.6k • 55 -
openai/whisper-base
Automatic Speech Recognition • Updated • 1.16M • 259 -
openai/whisper-base.en
Automatic Speech Recognition • 72.6M • Updated • 77.8k • 40 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 779k • 421 -
openai/whisper-tiny.en
Automatic Speech Recognition • Updated • 118k • 112