Ryan O'Connor

Hey there @AndrewBaker - training indeed does take a while, I stripped off many of the bells and whistles discovered/invented over the last couple of years in making diffusion models...

@jinfagang We trained for a bit using conceptual captions, but given that the implementation is designed for educational purposes and strips off many of the amazing improvements made in Diffusion...

Hi @night3759 - I think you might be thinking of the Stable Diffusion model? That has v1.4 weights that you can find [here](https://www.assemblyai.com/blog/how-to-run-stable-diffusion-locally-to-generate-images/#step-5-download-stable-diffusion-weights)

@ploeber the `STT` interface requires that the abstract async method `_main_task` is implemented. Currently `_main_task` exists as an instance attribute of `SpeechStream` - I'm not sure how to reconcile this

@ploeber could you test the current changes when you find some time tomorrow?

@ploeber addressed the rest of your comments 🙏

@theomonnom signed!

When I click on the CLA it says `You have agreed to the CLA for livekit/agents` - not sure why it's not updating

@davidzhao all set!