Python · Apache-2.0
PaddlePaddle/PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
★ 92.3k
Stars
11.6k forks · 260 open issues
+53/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
58.3
Momentum / 100
see the breakdown below
6y ago
Created
last push 53d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 33.1 | +53/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.99× the monthly pace |
| Freshness | 15 | 10.8 | last push 53d ago; decays to zero at 180 days |
| Scale | 15 | 14.4 | 92.3k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 58.3 | sum of the above |
Detail
| Topics | ai4sciencechineseocrdocument-parsingdocument-translationkieocrpaddleocr-vlpdf-extractor-ragpdf-parserpdf2markdownpp-ocrpp-structurerag |
| Matched on | RAG (rag) |
| Short window | +371 stars over 7 days = 53.0/day |
| Long window | +1.4k stars over 26 days = 53.6/day |
| Lifetime average | 38.91 stars/day over 2,372 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |