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 52 days ago
2 comments
bogu_mogu 52 days ago
cool, whats the datasets and teacher models?
link
antonios_makro 52 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 52 days ago
anywhere we can see it in action?
link
antonios_makro 52 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