Improve HF integration

[NielsRogge]

Hi @haidog-yaqub and team,

Niels here from the open-source team at Hugging Face. I discovered your work through the daily papers: https://huggingface.co/papers/2409.10819 (feel free to claim authorship with your HF account). I work together with AK on improving the visibility of researchers' work on the hub.

I see you already made a demo on the 🤗 hub which is great. I've got a couple of suggestions on improving the HF integration:

• would be great to link the demo to the paper, I opened https://huggingface.co/spaces/OpenSound/EzAudio/discussions/6 for that
• currently, all checkpoints are present inside the Space. Would be great to instead push them to dedicated model repos. See the guide below for more info.

We can then also add tags to the model repos, such as pipeline_tag: text-to-audio, so that people find your models at https://huggingface.co/models?pipeline_tag=text-to-audio&sort=trending.

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading. In case the models are custom PyTorch model, we could probably leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to each model. 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. Moreover, we can then link the checkpoints to the paper page, improving their visibility.

Let me know if you're interested/need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗

cc @Vaibhavs10