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
commentedon an article 1 day ago
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters liked a Space 4 days ago
baidu/Unlimited-OCR updated a model 7 days ago
PaddlePaddle/PaddleOCR-VL-1.5Organizations
commented on PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters 1 day ago
Add new model metadata so the model card gets a pointer to the newer version of the model
#97 opened 8 days ago
by
davanstrien
upvoted a paper 12 days ago
英文版面分析不太行
1
#6 opened 4 months ago
by
Macropodus
upvoted an article 13 days ago
Article
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
PaddlePaddle
• • 26published an article 13 days ago
Article
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters
PaddlePaddle
• • 26can you do an Indic only version? (devanagari)
1
#1 opened 21 days ago
by
trysem
Inference speed
2
#1 opened 17 days ago
by
johnlockejrr
upvoted a paper 17 days ago