Whisper
📉
2.7k
Transcribe audio files and YouTube videos 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 • 48 -
openai/whisper-large-v2
Automatic Speech Recognition • Updated • 80.6k • 1.78k -
openai/whisper-large
Automatic Speech Recognition • Updated • 33.3k • 530 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 513k • 275 -
openai/whisper-medium.en
Automatic Speech Recognition • 0.8B • Updated • 28.7k • 57 -
openai/whisper-small
Automatic Speech Recognition • Updated • 2.12M • 519 -
openai/whisper-small.en
Automatic Speech Recognition • 0.2B • Updated • 42.9k • 55 -
openai/whisper-base
Automatic Speech Recognition • Updated • 1.26M • 252 -
openai/whisper-base.en
Automatic Speech Recognition • 72.6M • Updated • 29.6k • 39 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 527k • 405 -
openai/whisper-tiny.en
Automatic Speech Recognition • Updated • 50.7k • 111