What’s your secret to superb audio recognition? Whisper it. We mean that literally—Whisper is the latest in OpenAI’s growing suite of models aimed to benefit humanity. On this episode of Five-Minute Friday, host Jon Krohn reviews OpenAI’s latest model, Whisper. This tool will vastly improve the way human speech is recognized and converted to text. Jon gets under the hood to show how the team managed to get such a powerfully accurate recognition model. Listen to the episode and find out how you can try it yourself, for free!
Additional materials: www.superdatascience.com/620
Interested in sponsoring a SuperDataScience Podcast episode? Visit JonKrohn.com/podcast for sponsorship information.
Source by Super Data Science: ML & AI Podcast with Jon Krohn
