fuyingw

/

MELP_Encoder

like 0

This PR improves the model card for the MELP model by:

• Adding the pipeline_tag: audio-text-to-text to the metadata, ensuring the model can be found at https://huggingface.co/models?pipeline_tag=audio-text-to-text.
• Populating the model description and direct use cases with information from the paper abstract.
• Adding a direct link to the paper at https://huggingface.co/papers/2506.21803.
• Adding the license: apache-2.0 to the metadata.
• Including a basic transformers usage example.
• Adding the BibTeX and APA citations for the paper.

Please review and merge.