I'm already used to the great videos of the youtube channel TwoMinutePapers.
In this video I'm not showing you anything about graphics, from my point of view I'm rather showing you what there is in the level of artificial intelligence - good design in the field of algorithms.
Whisper is an automatic speech recognition (ASR) system trained on 680,000 hours of multilingual and multitask supervised data collected from the web. We show that the use of such a large and diverse dataset leads to improved robustness to accents, background noise and technical language. Moreover, it enables transcription in multiple languages, as well as translation from those languages into English. We are open-sourcing models and inference code to serve as a foundation for building useful applications and for further research on robust speech processing., see Open AI blog page.
