Improve model card: Add pipeline tag, library name, project page link, and sample usage

#1
by nielsr HF Staff - opened

This PR improves the model card by:

  • Adding the pipeline_tag: audio-to-audio to the metadata, enabling easier discovery on the Hugging Face Hub at https://huggingface.co/models?pipeline_tag=audio-to-audio.
  • Including library_name: transformers in the metadata, as evidence from config.json and the model's architecture suggests compatibility with the Hugging Face transformers library, which will enable the automated "how to use" widget.
  • Adding an explicit link to the project page (https://freedomintelligence.github.io/EchoX/) in the top section of the model card.
  • Replacing the generic "Usage" section with a comprehensive "Sample Usage" section, including environment setup, model download, and inference commands directly from the official GitHub repository's README, allowing users to quickly get started.
  • Correcting the training data size in the "Model Description" from 10k hours to 6k hours, aligning with the paper's abstract and the GitHub README.

These changes provide more comprehensive information and improve user experience on the Hugging Face Hub.

Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment