VOTF Episode: 10 Whisper by OpenAI: Everything you need to know about the latest in open source speech recognition
About this episode
Last week was a big week for speech intelligence with OpenAI’s release of Whisper, an open-source speech recognition model. At Deepgram, we’re excited about Whisper’s end-to-end deep learning approach and the splash it made in speech tech, since we’ve been building speech models using end-to-end deep learning for nearly a decade. So what does Whisper mean for the future of artificial intelligence in speech? In this episode, we take a closer look at Whisper: its features and functionality, its limitations, the use cases it’s best suited for, and more.
Right now, you can try Whisper via the Deepgram API. Learn more here.
Host & Guests
Scott Stephenson is a dark matter physicist turned Deep Learning entrepreneur. He earned a PhD in particle physics from University of Michigan where his research involved building a lab two miles underground to detect dark matter. Scott left his physics post-doc research position to found Deepgram.
Nick works closely with the Deepgram research team to bring world class language models to our customers.