Downloads · 30 days
0
EgoSpeak
kjunh/EgoSpeak
EgoSpeak is a machine learning model from kjunh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repo contains final checkpoints for the EgoSpeak project. - Models: lstr, mamba, miniroad - Datasets: easycom, ego4dshuffle, ytconvpretrained - Modalities: A (audio), V (video), AV (audio+video)
Access
Public
Updated Feb 11, 2025
Repo size
8.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth8.5 GB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Jan 8, 2025
- Updated
- Feb 11, 2025
- SHA
- 15106c02
Model card
From the Hugging Face model README
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
- License
- apache-2.0
- Created
- Jan 8, 2025
- Updated
- Feb 11, 2025