Hacker News new | ask | show | jobs
Show HN: Open dataset for distilling GPU audio2face models to CPU students (huggingface.co)
3 points by antonios_makro 6 days ago
2 comments
bogu_mogu 5 days ago
cool, whats the datasets and teacher models?
link
antonios_makro 5 days ago
datasets: CREMA-D / RAVDESS / TESS / JL Corpus models: NVIDIA A2F - 3D, LAM audio2 expression, check the HF page for links
link
goran-j 5 days ago
anywhere we can see it in action?
link
antonios_makro 5 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
link