espnet

/

mixdata_svs_visinger2_spkemb_lang_pretrained_avg

like 0

Follow

ESPnet 351

This PR improves the model card for the SingingSDS system by:

• Linking to the official paper: SingingSDS: A Singing-Capable Spoken Dialogue System for Conversational Roleplay Applications.
• Adding the pipeline_tag: text-to-audio to enhance discoverability on the Hugging Face Hub.
• Including links to the GitHub repository and the Hugging Face Space demo.
• Providing comprehensive sections on installation, usage (CLI and Web Interface), and configuration, directly sourced from the project's GitHub README.
• Updating the "Paper Coming Soon" badge to link to the published paper.

The library_name has not been added as the system integrates multiple components from various libraries, making a single library_name for an automated snippet inappropriate based on guidelines.

Please review and merge this PR if everything looks good.