EgoSpeak Checkpoints
This repo contains final checkpoints for the EgoSpeak project.
- Models:
lstr,mamba,miniroad - Datasets:
easycom,ego4dshuffle,ytconv_pretrained - Modalities:
A(audio),V(video),AV(audio+video)
File Naming Convention
mamba_easycom_A.pth→ Mamba model, trained on EasyCom, audio-only
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no library tag.