TECH NEWS: OpenAI open sources Whisper, a speech recognition system that was trained on 680K hours of "multilingual and multitask supervised data collected from the web" (Kyle Wiggers/TechCrunch)

Wednesday, 21 September 2022

OpenAI open sources Whisper, a speech recognition system that was trained on 680K hours of "multilingual and multitask supervised data collected from the web" (Kyle Wiggers/TechCrunch)

via Techmeme https://ift.tt/30xVNdp

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)