Apply for community grant: Personal project (gpu)
Hello HF 🤗, and happy new year! 🎆
I'm releasing the first iteration of a project I've been working on for quite awhile. It's called Taproot, and it's a seamlessly scalable open-source AI/ML inference engine designed for letting developers build real-time experiences clustered across a small-to-mid-sized cluster without needing the overhead of hyperscale infrastructure.
Along with the server and task framework is a client library for node and the browser, along with a real-time hands-free voice assistant that can run on mid-level devices in <12GB VRAM, with web search, weather, and other tools. It uses my real-time browser wake-word library to detect utterances of the phrase 'Hey Vox', 'Hi Vox', 'Okay Vox', 'Anachrovox' or just 'Vox' (alongside some others.)
Right now I've configured three small T4 spaces to balance between each other using Taproot. This should keep them all nice and responsive no matter which front-end someone is using. Their links are:
https://huggingface.co/spaces/benjamin-paine/anachrovox-emerald
https://huggingface.co/spaces/benjamin-paine/anachrovox-amber
https://huggingface.co/spaces/benjamin-paine/anachrovox-azure
Since scaling and being flexible on hardware is the main selling point of Taproot, I am similarly flexible on the kind of GPU grant I'm asking for to deploy it - I figured you guys may have some hardware that's harder to rent than others, so I'd be happy to accept whatever you've got that's left over.
Everything is open-source of course! Links below.
Taproot: https://github.com/painebenjamin/taproot
Taproot JS Client: https://github.com/painebenjamin/taproot.js
Anachrovox: https://github.com/painebenjamin/anachrovox
Hello! If you find this request, I had to move the repository this is one, it's unfortunately entered that bugged state where it can't be rebuilt and can't be started. :( But the links above should still point to the working ones.