|
Download README.md from MYRASHARMA/study-asr: direct link, hf CLI and curl.
- Browser
- Download file 727 Bytes
-
https://huggingface.co/MYRASHARMA/study-asr/resolve/main/README.md
- Command line
-
hf download hf://MYRASHARMA/study-asr/README.md
-
curl -L -o README.md https://huggingface.co/MYRASHARMA/study-asr/resolve/main/README.md
727 Bytes
metadata
license: cc-by-4.0
tags:
- adamw
- contrastive
- exponential
- gated-fusion
- huge
- mish
- orthogonal
- scalenorm
- standard
- swin-t
main.py
Model Overview
A huge-scale implementation of the swin t architecture, built for contrastive tasks.
Architecture
- Architecture: swin t
- Scale: huge
- Attention: standard
- Fusion strategy: gated fusion
- Task head: contrastive
- Activation: mish
- Normalization: scalenorm
- Initialization: orthogonal
Training
- Optimizer: adamw
- LR scheduler: exponential
Files
main.py— main artifact of this repository
License
See the license field above.