Add model card and metadata

Hi! I'm Niels from the Hugging Face community team. I'm opening this PR to provide a more detailed model card for PianoKontext. It includes relevant metadata (pipeline tag) and links to the paper, code, and project page to make the model more discoverable and better documented for users.

README.md

@@ -1,5 +1,27 @@
 ---
 license: cc-by-nc-sa-4.0
+pipeline_tag: audio-to-audio
 ---
 
-A pretrained PianoKontext model from [PianoKontext: Expressive Performance Rendering from Deadpan Context](arxiv.org/abs/2606.12282)
+# PianoKontext: Expressive Performance Rendering from Deadpan Context
+
+PianoKontext is a flow matching rendering model for classical piano music that generates variable-length performances in the latent space of a pretrained Music2Latent model.
+
+- **Paper:** [PianoKontext: Expressive Performance Rendering from Deadpan Context](https://huggingface.co/papers/2606.12282)
+- **GitHub Repository:** [realfolkcode/pianokontext](https://github.com/realfolkcode/pianokontext)
+- **Project Page & Demos:** [PianoKontext Demo](https://realfolkcode.github.io/pianokontext_demo)
+- **Interactive Demo:** [Open In Colab](https://colab.research.google.com/drive/1cKoKdoRKZd89gvBsnhYdsxyKsR-bS9QP?usp=sharing)
+
+## Description
+Expressive performance rendering (EPR) aims to generate realistic performances constrained on sequences of notes. PianoKontext addresses the limitations of existing flow matching models regarding expressive timing by generating variable-length performances. It synthesizes MIDI scores into deadpan audio and employs Dynamic Time Warping (DTW) in the latent space to construct paired data for training. The aligned embeddings are concatenated in DiT blocks, allowing the model to learn the dependencies between the score and expressive performances.
+
+## Citation
+If you use this model in your research, please cite the following paper:
+```bibtex
+@article{gavrilev2026pianokontext,
+  title={PianoKontext: Expressive Performance Rendering from Deadpan Context},
+  author={Dmitrii Gavrilev},
+  journal={arXiv preprint arXiv:2606.12282},
+  year={2026}
+}
+```