fdugyt

/

XY_Tokenizer

like 1

This PR significantly improves the model card for the XY-Tokenizer model by:

• Adding comprehensive details: The full content from the project's GitHub README has been integrated, including an overview, key highlights, installation instructions, and usage examples.
• Enhancing discoverability: The pipeline_tag: audio-to-audio has been added to the metadata, ensuring the model can be easily found under relevant tasks on the Hugging Face Hub (https://huggingface.co/models?pipeline_tag=audio-to-audio).
• Specifying the library: The library_name: pytorch tag has been added, indicating the primary framework used for the model.
• Providing essential links: Direct links to the paper (XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs), the official GitHub repository (https://github.com/gyt1145028706/XY-Tokenizer), and the Hugging Face model page are now prominently featured.
• Cleaning up content: Broken or unconfirmed links (e.g., for blog/demos) have been removed or updated, and the image path has been corrected for rendering on the Hub.

Please review and merge this PR to provide a more complete and helpful resource for the community.