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 • 75.4k • 1.79k -
openai/whisper-large
Automatic Speech Recognition • 2B • Updated • 83.8k • 542 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 742k • 284 -
openai/whisper-medium.en
Automatic Speech Recognition • 0.8B • Updated • 41.7k • 58 -
openai/whisper-small
Automatic Speech Recognition • Updated • 1.93M • 549 -
openai/whisper-small.en
Automatic Speech Recognition • 0.2B • Updated • 39.7k • 56 -
openai/whisper-base
Automatic Speech Recognition • Updated • 1.76M • 265 -
openai/whisper-base.en
Automatic Speech Recognition • 72.6M • Updated • 32.1k • 41 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 811k • 425 -
openai/whisper-tiny.en
Automatic Speech Recognition • 37.8M • Updated • 111k • 115