espnet

/

aceopencpop_svs_visinger2_40singer_pretrain

like 0

Follow

ESPnet 317

This PR updates the model card for the espnet/aceopencpop_svs_visinger2_40singer_pretrain model.

Key improvements include:

• Adding the pipeline_tag: text-to-audio to correctly categorize the model as a Singing Voice Synthesis (SVS) component.
• Adding library_name: espnet as evidenced by the model's nature as an ESPnet2 model and the provided usage instructions.
• Including direct links to the associated paper, the main SingingSDS GitHub repository, and the Hugging Face Space demo for broader context and discoverability.