Whisper-jax 70x faster text to speech

GPT-4: Whisper JAX is an optimized JAX implementation of OpenAI’s Whisper Model that runs over 70x…

Code and debug with Bard

Today, Google is updating Bard with the ability to help people with programming and software development…

Run GPT model on the browser with WebGPU.

An implementation of GPT inference in less than ~2000 lines of vanilla Javascript. GPT-4: WebGPU is…