Open Source libraries like Transformer.js allow you to run Machine Learning workloads right within your browser and even Supabase Edge Functions. We can perform multi-language speech recognition and translation, text-to-speech, and even RAG, fully offline and in-browser! In this lightning talk, Thor will take a look at some examples of what's possible, as well as a small look behind the scenes at the open source ONNX Runtime which makes this possible.

In this talk we'll take a look at the awesome open source library Transformers.js which allows us to run pretrained models right in the browser with no need for servers! Additionally we'll explore how we've brought AI inference and LLMs into Supabase Edge Functions, allowing you to run certain AI workloads faster and more cost-efficiently on the Edge!
—
Thor 雷神 is a Software Developer at Supabase working on DevRel and DX. He's also the organiser of HackerHouse Taiwan, aiming to bring Software Engineer from around the globe together to work from and explore Taiwan.