Public Protocol
Platform

Paper

Robust Speech Recognition via Large-Scale Weak Supervision (Whisper)

External resource. Not made or verified by Public Protocol.

OpenAI paper of December 2022 describing speech recognition models trained on 680,000 hours of multilingual, multitask audio, which the authors report approach human accuracy and robustness and are competitive on standard benchmarks without fine-tuning.

Go to the source

https://arxiv.org/abs/2212.04356

Maintainer
Radford and co-authors (OpenAI)
Licence, as stated at its source
arXiv non-exclusive distribution licence 1.0
Open or commercial
Not stated by the maker
Maturity
EstablishedOur reading, 16 November 2026
Safety
S0
Review
Listed 16 November 2026by Public Protocol editors
Checked
16 November 2026
Next check due
16 May 2027
Steward
Public Protocol editors

Where it sits in the blueprint

Stages

Learn

Context

Climate, setting, scale, cost and skill: not stated in this entry. Check the source against your own place and numbers.

Verification

No verification is recorded on Public Platform for this entry. Records are added when someone reads it for accuracy, reviews it with a stated qualification, builds it or measures it.

Record

How it came in

Seed catalogue, 16 November 2026. Listed from the sensors, robotics and AI machines research of 2026-11-16. The source was opened and described on the date shown.

Licence

arXiv non-exclusive distribution licence 1.0. Read at https://arxiv.org/abs/2212.04356. How licences are recorded