Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Netra-Lab
/
Netra-OCR
Like
0
Follow
Netra Lab
1
Image-to-Text
ONNX
Khmer
English
ocr
khmer-ocr
document-layout
netra-lab
License:
mixed
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
Netra-OCR
Commit History
Oct 31
3 days ago
20:06
Card: the PyTorch checkpoints in pytorch/, images from this repo
Darayut
Verified signature
c158e0a
20:04
Add the PyTorch checkpoints (pytorch/) and the model-card images (assets/)
Darayut
Verified signature
8ce5610
18:39
Store the recognizers' and layout model's weights in fp16 (half the download)
Darayut
Verified signature
04cb751
Weights are stored as fp16 and cast to float32 at load; ONNX Runtime folds the casts. CPU text identical on 325/325 lines, layout pages identical. lines/ unchanged. Model card updated for netra-ocr 1.2.0.
11:58
Netra Runtime bundles: recognition, recognition-blockwise, lines, layout
Darayut
Verified signature
ada0c60
11:56
initial commit
Darayut
Verified signature
2fae6e2