Hi @jiaqili3 🤗
Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2505.13000.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim
the paper as yours which will show up on your public profile at HF, add Github and project page URLs.
It's great to see that the core DualCodec models are already available on the Hugging Face Hub (under amphion/dualcodec)! I also noticed in your README that you've "Uploaded some TTS models (DualCodec-VALLE, DualCodec-Voicebox)" that can be automatically downloaded via your package.
It'd be awesome to make the checkpoints for these DualCodec-based TTS models (DualCodec-VALLE and DualCodec-Voicebox) explicitly available on the 🤗 hub, to improve their discoverability/visibility. We can add tags so that people find them when filtering https://huggingface.co/models. We could potentially create separate model repositories for them, which also helps with download statistics and better organization.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverages the hf_hub_download one-liner to download a checkpoint from the hub.
We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @jiaqili3 🤗
Niels here from the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2505.13000.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo for instance), you can also claim
the paper as yours which will show up on your public profile at HF, add Github and project page URLs.
It's great to see that the core
DualCodecmodels are already available on the Hugging Face Hub (underamphion/dualcodec)! I also noticed in your README that you've "Uploaded some TTS models (DualCodec-VALLE, DualCodec-Voicebox)" that can be automatically downloaded via your package.It'd be awesome to make the checkpoints for these DualCodec-based TTS models (DualCodec-VALLE and DualCodec-Voicebox) explicitly available on the 🤗 hub, to improve their discoverability/visibility. We can add tags so that people find them when filtering https://huggingface.co/models. We could potentially create separate model repositories for them, which also helps with download statistics and better organization.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, we could leverage the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto any customnn.Module. Alternatively, one can leverages the hf_hub_download one-liner to download a checkpoint from the hub.We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗