Show HN: Open dataset for distilling GPU audio2face models to CPU students

Show HN: Open dataset for distilling GPU audio2face models to CPU students(huggingface.co)

3 points by antonios_makro 24 days ago | 4 comments

bogu_mogu 24 days ago |

cool, whats the datasets and teacher models?

datasets: CREMA-D / RAVDESS / TESS / JL Corpus models: NVIDIA A2F - 3D, LAM audio2 expression, check the HF page for links

goran-j 24 days ago |

anywhere we can see it in action?

antonios_makro 24 days ago | |

This dataset powers our v2 version so not published yet, the v1 with no strong facial expression is in many places ..check myned.ai avatar, or nyxclaw.ai