Hacker News
Linking pages
Related searches:

Search whole site: site:twitter.com

Search title: Ryan Hileman on Twitter: "I just used 3,000 GPU-hours to test all 9 new OpenAI Whisper speech recognition models, two Talon acoustic models, and NVIDIA Nemo large and xlarge models. Whisper has a peculiar failure case. Here's what I think." / Twitter

See how to search.