Improve model card: add pipeline tag, paper link, and sample usage

by nielsr HF Staff - opened Sep 11, 2025

←

This PR enhances the model card for kyutai/stt-2.6b-en by:

Adding pipeline_tag: automatic-speech-recognition to the metadata for improved discoverability on the Hugging Face Hub.
Adding a prominent link to the associated paper, "Streaming Sequence-to-Sequence Learning with Delayed Streams Modeling", at the top of the card.
Replacing the general "How to Get Started with the Model" section with a concrete "Sample Usage" code snippet from the official GitHub repository, making it easier for users to get started.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment