whisper
Robust Speech Recognition via Large-Scale Weak Supervision
Audio & Video
Robust Speech Recognition via Large-Scale Weak Supervision
Open product
Robust Speech Recognition via Large-Scale Weak Supervision. [[Blog]]( [[Paper]]( [[Model card]]( [[Colab example]]( Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
Disclosure. Listings are free. Boosted placement is a paid, clearly-labelled promotion and never affects editor's picks or the organic Top rated order.