OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and evaluation benchmark, commercial-grade OCR and Document Parsing systems, and faithful reproductions of the core implementations from a wide range of academic papers.
active 2024-05-31 → 2026-06-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 740 days from 2024-05-31 to 2026-06-09. Pushes: 106 total, peak 6 in a day. Pull requests: 47 total, peak 4 in a day. Issues: 96 total, peak 15 in a day. Comments: 213 total, peak 13 in a day. Stars: 600 total, peak 19 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| Topdu | 286 | 106 | 35 | 117 |
| nissansz | 20 | 0 | 0 | 16 |
| hp0716 | 11 | 0 | 0 | 9 |
| py0student | 7 | 0 | 0 | 4 |
| gaozhun | 6 | 0 | 0 | 5 |
| FahNos | 6 | 0 | 0 | 3 |
| super-tian | 6 | 0 | 0 | 4 |
| ir2718 | 5 | 0 | 1 | 4 |
| leduy-it | 5 | 0 | 0 | 2 |
| oggyfaker | 5 | 0 | 0 | 2 |
| dlml | 4 | 0 | 0 | 2 |
| AnkhXXX | 4 | 0 | 0 | 4 |
| zhuzhiqiang148 | 4 | 0 | 0 | 4 |
| dotneet | 3 | 0 | 2 | 0 |
| kongyan66 | 3 | 0 | 0 | 2 |
| aaa244aaa | 3 | 0 | 0 | 0 |
| ThanhPham1987 | 3 | 0 | 0 | 1 |
| rowerking | 3 | 0 | 0 | 1 |
| imneonizer | 3 | 0 | 0 | 1 |
| ruc-G | 3 | 0 | 0 | 3 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#205Topdu2026-06-09 13:11可以支持vllm部署么，当前实测吞吐只有30 tokens/s
- Pull request#201babywakeup2026-04-23 07:34
- Issue#197ZidunGuo2026-04-07 14:49A issule about Chinese benchmark evaluation
- Issue comment#191Topdu2026-03-02 07:05openrec/modeling/decoders/nrtr_decoder.py中的self.out_channels数值问题
- Issue comment#193Topdu2026-03-02 07:00PDF 识别有时存在问题
- Issue#193runzezhu783-cmd2026-03-02 02:56PDF 识别有时存在问题
- Issue#191maomaoyuchengzi2026-02-28 09:27openrec/modeling/decoders/nrtr_decoder.py中的self.out_channels数值问题
- Issue#189liuzhuosin2026-02-10 06:25源码部署后测试出现TypeError: filter_overlap_boxes() missing 1 required positional argument: 'layout_shape_mode'
- Issue comment#186champiom6662026-02-04 06:53OpenDoc-0.1B模型在哪下载？
- Issue comment#184Topdu2026-02-02 09:12有表格的pdf会识别错误
- Pull request#182superkura2026-02-02 06:12
- Pull request#183RinZ272026-01-31 07:01
- Issue comment#146FahNos2026-01-15 16:13Long text custom training + Image size in config problem
- Issue comment#146maomaoyuchengzi2026-01-15 03:36Long text custom training + Image size in config problem
- Issue#175ningpp2026-01-10 04:06how to convert unirec-0.1b to onnx
- Issue comment#175ningpp2026-01-10 04:06how to convert unirec-0.1b to onnx
- Issue comment#174Topdu2026-01-09 09:25Several questions on OpenDoc-0.1B
- Issue comment#174dt-yy2026-01-09 03:23Several questions on OpenDoc-0.1B
- Issue comment#178alephpi2026-01-07 17:19Availability of pretrained model for English (openocr_svtrv2_en)?
- Issue comment#175Topdu2026-01-07 11:29how to convert unirec-0.1b to onnx
- Issue#178pvd0anh2026-01-06 08:05Availability of pretrained model for English (openocr_svtrv2_en)?
- Issue comment#173dlml2026-01-05 04:14How to train the model UniRec-0.1B ？
- Issue#176iamxiaojianzheng2026-01-05 03:30根据文档无法复现无法成功使用模型
- Issue comment#173Topdu2026-01-05 03:19How to train the model UniRec-0.1B ？
- Issue#174alephpi2025-12-26 20:34Training dataset for OpenDoc-0.1B
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 600 stars here means stars gained during the window, not the repo's star count.