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 • 2B • Updated • 66.8k • 1.79k -
openai/whisper-large
Automatic Speech Recognition • 2B • Updated • 84.8k • 542 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 526k • 283 -
openai/whisper-medium.en
Automatic Speech Recognition • 0.8B • Updated • 41.8k • 58 -
openai/whisper-small
Automatic Speech Recognition • Updated • 1.9M • 547 -
openai/whisper-small.en
Automatic Speech Recognition • 0.2B • Updated • 63.9k • 56 -
openai/whisper-base
Automatic Speech Recognition • Updated • 1.57M • 264 -
openai/whisper-base.en
Automatic Speech Recognition • 72.6M • Updated • 81.1k • 41 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 754k • 424 -
openai/whisper-tiny.en
Automatic Speech Recognition • 37.8M • Updated • 97k • 113