The tiny version already runs at 97ms in-browser. For even lower latency, try some engineering trade-offs on top of it—like optimizing the pre and post-processing steps.
👋 Open to Work
cuicheng
ChengCui
AI & ML interests
None yet
Recent Activity
new activity about 2 hours ago
PaddlePaddle/PP-OCRv6_tiny_rec_onnx:Some people steal from you new activity about 2 hours ago
PaddlePaddle/PP-OCRv6_medium_rec:Demo for this model on Spaces new activity about 2 hours ago
PaddlePaddle/PP-OCRv6_medium_det:Inference speedOrganizations
Some people steal from you
2
#1 opened 19 days ago
by 
johnlockejrr
Demo for this model on Spaces
1
#1 opened 5 days ago
by 
multimodalart
Inference speed
3
#1 opened 20 days ago
by johnlockejrr
commented on PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters 5 days ago
liked a
Space 7 days ago
updated a
model 11 days ago
Add new model metadata so the model card gets a pointer to the newer version of the model
#97 opened 11 days ago
by 
davanstrien
liked a
model 12 days ago
upvoted a paper 15 days ago
英文版面分析不太行
1
#6 opened 4 months ago
by 
Macropodus
upvoted an article 16 days ago
Article
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
PaddlePaddle
• • 26 published an article 16 days ago
Article
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
PaddlePaddle
• • 26 liked a
Space 16 days ago
liked a
model 16 days ago
authored a
paper 20 days ago
can you do an Indic only version? (devanagari)
1
#1 opened 25 days ago
by 
trysem
updated 2
models 20 days ago
updated a
dataset 20 days ago