Update README.md

README.md

@@ -1,6 +1,39 @@
----
-license: other
-license_name: nvidia-open-model-license
-license_link: >-
-  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
----
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: >-
+  https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/
+---
+# Audio2Face-3D
+
+## Description
+**Audio2Face-3D** leverages state-of-the-art deep learning techniques to transform audio input into highly detailed facial animations. By utilizing a high-quality 4D capture dataset and sophisticated network architectures, our system can produce realistic facial animations of skin, teeth, tongue, and eyeballs. The system supports real-time interaction, making it suitable for both live applications and offline facial animation authoring.
+
+**Model Developer**: NVIDIA
+
+## Model Versions
+The Audio2Face-3D release includes 
+* [Audio2Face-3D-v3.0](https://huggingface.co/nvidia/Audio2Face-3D-v3.0) (diffusion-based network for multiple identities)
+* [Audio2Face-3D-v2.3-Mark](https://huggingface.co/nvidia/Audio2Face-3D-v2.3-Mark) (regression-based network for Mark identity)
+* [Audio2Face-3D-v2.3-Claire](https://huggingface.co/nvidia/Audio2Face-3D-v2.3-Claire) (regression-based network for Claire identity)
+* [Audio2Face-3D-v2.3-James](https://huggingface.co/nvidia/Audio2Face-3D-v2.3-James) (regression-based network for James identity)
+
+Note, all networks receive common inputs of audio and emotion labels and output motion deltas for facial skin, tongue, jaw, and eyeballs.
+
+## Correspondence to
+Yeongho Seol ([email protected]), Michael Huang ([email protected])
+
+
+## License
+Your use of this model is governed by the [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/).
+
+
+## Citation
+```
+@article{chung2025audio2face,
+  title={Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars},
+  author={Chung, Chaeyeon and Fedorov, Ilya and Huang, Michael and Karmanov, Aleksey and Korobchenko, Dmitry and Ribera, Roger and Seol, Yeongho},
+  journal={arXiv preprint arXiv:00000000},
+  year={2025}
+}
+```