Whisper
📉
2.7k
Transcribe or translate audio 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 • 49 -
openai/whisper-large-v2
Automatic Speech Recognition • Updated • 82.1k • 1.78k -
openai/whisper-large
Automatic Speech Recognition • Updated • 33.1k • 531 -
openai/whisper-medium
Automatic Speech Recognition • Updated • 510k • 276 -
openai/whisper-medium.en
Automatic Speech Recognition • 0.8B • Updated • 32.4k • 57 -
openai/whisper-small
Automatic Speech Recognition • Updated • 2.22M • 523 -
openai/whisper-small.en
Automatic Speech Recognition • 0.2B • Updated • 89.1k • 55 -
openai/whisper-base
Automatic Speech Recognition • Updated • 1.07M • 253 -
openai/whisper-base.en
Automatic Speech Recognition • 72.6M • Updated • 31.3k • 40 -
openai/whisper-tiny
Automatic Speech Recognition • Updated • 562k • 410 -
openai/whisper-tiny.en
Automatic Speech Recognition • Updated • 63.8k • 111