Spaces:
Runtime error
Apply for a GPU community grant: Academic project
Dear Hugging Face Team,
We are writing to request a GPU grant for our Space to support real-time Singing Voice Synthesis demos of YingMusic-Singer.
Project Overview
YingMusic-Singer is a singing voice synthesis system capable of generating songs with strong prosody adherence, even when lyrics have been modified, translated, or code-switched across languages. Our paper has been submitted to InterSpeech 2026, and the arXiv preprint will be available soon.
Resources
Checkpoints: Hugging Face Model Page
We have launched a Hugging Face Space for interactive demos. However, CPU-only inference is prohibitively slow for a smooth user experience. A GPU grant would enable real-time singing voice synthesis and allow the community to seamlessly explore YingMusic-Singer's capabilities.
We believe accessible, high-performance demos are key to advancing music AI research and fostering community engagement.
Thank you very much for your consideration!
Best regards, ASLP-lab
Hi @ASLP-lab , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of this page so your Space can run on ZeroGPU.
If you can, we ask that you upgrade to Pro ($9/month) to enjoy higher ZeroGPU quota and other features like Dev Mode, Private Storage, and more: hf.co/pro