Tech
Open source OpenAI whisper, a speech recognition system trained for 680K hours "Multilingual and multitasking monitored data collected from the web" (Kyle Wiggers / TechCrunch)
Kyle Wiggers / TechCrunch:
Open source OpenAI Whisper, a speech recognition system that has been trained for over 680k hours on “multilingual and multitasking monitored data collected from the web”– Speech recognition is still a challenging problem in AI and machine learning. In one step to solve it…
Source link