Hi @Bing0cv 🤗

I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work on Arxiv and your project page (https://aslp-lab.github.io/MeanVC). It's fantastic to see the advancements in lightweight and streaming zero-shot voice conversion with MeanVC!

I noticed in your GitHub README that you have a plan to release the "HuggingFace model" and "inference code" soon, as stated in your TODO list and the "Code and models will be released soon" banner. That's great news!

Would you like to host the MeanVC model you've pre-trained on https://huggingface.co/models once it's released?
Hosting on Hugging Face will give you more visibility and enable better discoverability. We can add tags in the model cards (e.g., "audio-to-audio" for your voice conversion model) so that people find the models easier, link it to your paper page (https://huggingface.co/papers/2510.08392), etc.

If you're down, here's a guide: https://huggingface.co/docs/hub/models-uploading. If it's a custom PyTorch model, you can use the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to the model, allowing you to upload the model and people to download and use it right away. Alternatively, people can use hf_hub_download to download the model directly.

You can also build a demo for your model on Spaces, and we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.

Let me know if you're interested or need any guidance as you prepare for the release!

Kind regards,

Niels