Robust Speech Recognition via Large-Scale Weak Supervision

Published on Dec 6, 2022


We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual and multitask supervision, the resulting models generalize well to standard benchmarks and are often competitive with prior fully supervised results but in a zero-shot transfer setting without the need for any fine-tuning. When compared to humans, the models approach their accuracy and robustness. We are releasing models and inference code to serve as a foundation for further work on robust speech processing.


This comment has been hidden

Sign up or log in to comment

Models citing this paper 106

Browse 106 models citing this paper

Datasets citing this paper 2

Spaces citing this paper 1423

Collections including this paper 8