MM-Turn-Taking-Candor-AVCocktail
Collection
Pretrained models related to Candor & AVCocktail datasets. • 11 items • Updated
MMVAP — Candor
Audio-visual early-fusion Voice Activity Projection (VAP) turn-taking model.
Training data: Trained from scratch on the Candor corpus.
Checkpoint: Fold 0, epoch 10.
Files
config.yamlweights.pt
Source code
This checkpoint was produced with mm-turn-taking.
- Downloads last month
- 12
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support