In this video, we take a look at the newest addition from OpenAI, Whisper.
Whisper is an open source automatic speech recognition system that can transcribe speech to text with 50% fewer errors than previous models.
The new model is robust to accents, background noise, and technical language, and also enables transcription in 99 different languages.
The system has full support for punctuation and was trained on 680,000 hours of multilingual data collected from the Internet.
00:00 Intro to Whisper OpenAI
00:20 What is OpenAI Whisper?
00:57 Tip 1
03:43 Tip 2
