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.
PaddlePaddle/PaddleOCR is accelerating — star growth is speeding up by +12.1/day (94th percentile in the tracked cohort), on top of +61.1 stars/day. Forks are climbing too, at +7.4/day.
Elevated breakout odds over the next 14 days, led by star acceleration (94th pctl) and star velocity (92th pctl). Confidence is high given the available history.
~16 forks/day, 3.1× the trailing baseline.
~24 forks/day, 3.4× the trailing baseline.
~10 forks/day, 4.4× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/PaddlePaddle/PaddleOCR)Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
Reconstructed from 359 snapshots — the time-series GitHub’s API doesn’t expose.
~20 forks/day, 5.7× the trailing baseline.
~18 forks/day, 3.6× the trailing baseline.
~24 forks/day, 4.2× the trailing baseline.
~19 forks/day, 16.1× the trailing baseline.
~13 forks/day, 9.6× the trailing baseline.
~14 forks/day, 3.6× the trailing baseline.
~20 forks/day, 3.1× the trailing baseline.
~26 forks/day, 7.8× the trailing baseline.
~15 forks/day, 8.6× the trailing baseline.