Demo for this model on Spaces
Hi @naklecha 🤗
I'm Apolinario, from the open-source team at Hugging Face. Congrats and thanks for open-sourcing naklecha/caramel-1 on the Hub! We were excited about this work and built with an agent an interactive demo app of it on Hugging Face Spaces, running on a free ZeroGPU infrastructure.
Here's a link to the demo: https://huggingface.co/spaces/hugging-apps/caramel-1
We would love to transfer this demo to you or your organization. Would you like this demo to live under your own account or organization? If so just let me know here which username to transfer to, and we'll transfer the Space over to you, we hope it can give your work more visibility, discoverability and allows folks to try it out.
(If you have any questions or just want to chat more about this, you can find me on Twitter, LinkedIn or apolinario @ huggingface.co)
Cheers,
Poli
hey poli, thank you so much, this is awesome! you could transfer it to naklecha.
one small thing i noticed: in "talk to caramel" mode caramel's own channel starts empty, so it has to invent a voice from nothing and sounds a lot worse than the samples. putting a few seconds of a fixed voice on caramel's channel before the user speaks would help a lot, and a couple of stereo two-person openings as examples would get it closer to the blog samples. if it's easier, i'm also happy to make these changes myself after the transfer!
thanks again for building this, really appreciate it :')