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.
-
2.38k
Whisper
📉Transcribe audio from microphone, file, or YouTube video
-
Robust Speech Recognition via Large-Scale Weak Supervision
Paper • 2212.04356 • Published • 35 -
openai/whisper-large-v2
Automatic Speech Recognition • 2B • Updated • 209k • 1.75k -
openai/whisper-large
Automatic Speech Recognition • 2B • Updated • 73.6k • 521