NormXU / nougat-latex-ocr
Codebase for fine-tuning / evaluating nougat-based image2latex generation models
☆135Updated 4 months ago
Alternatives and similar repositories for nougat-latex-ocr:
Users that are interested in nougat-latex-ocr are comparing it to the libraries listed below
- Formula recognition based on LaTeX-OCR and ONNXRuntime.☆324Updated 2 months ago
- TexTeller can convert image to latex formulas (image2latex, latex OCR) with higher accuracy and exhibits superior generalization ability,…☆433Updated 5 months ago
- UniMERNet: A Universal Network for Real-World Mathematical Expression Recognition☆263Updated last month
- A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.☆161Updated 8 months ago
- A High-efficiency Open-source Toolkit for Table-to-Latex Task☆195Updated last month
- Another LaTex equation OCR tool based on ConvNeXt and Transformer☆47Updated last year
- Large scale training of Latex formula recognition model, currently being organized and open source☆47Updated 9 months ago
- 基于序列表格识别算法推理库,集成PP-Structure和modelscope等表格识别算法。☆181Updated 2 weeks ago
- LaTeX OCR 的数据仓库☆107Updated 7 months ago
- YOLO models trained by DocLayNet - power your Document Intelligent by Layout Analysis☆83Updated 3 weeks ago
- Math OCR model that outputs LaTeX and markdown☆1,008Updated this week
- ☆74Updated last month
- 阅读顺序、Layoutreader☆11Updated 8 months ago
- Analysis of Chinese and English layouts 中英文版面分析☆160Updated last month
- Chinese Mathematical Formula Detection (MFD) Dataset 中文文档数学公式检测数据集☆33Updated 2 years ago
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆136Updated 7 months ago
- 基于TrOCR + UniMER-1M数据集,训练一个小而美的公式识别模型☆19Updated 2 months ago
- 【间隙·树·排序算法】 对OCR结果或PDF提取的文本进行版面分析,按人类阅读顺序进行排序。☆120Updated 11 months ago
- 文档方向分类☆210Updated 2 months ago
- Object Detection Model for Scanned Documents☆86Updated last year
- DocTr++ in PaddlePaddle☆43Updated 6 months ago
- 如需体验textin文档解析,请点击https://cc.co/16YSIy☆72Updated 2 months ago
- 基于Pytorch实现的End-to-End图像Latex公式识别 inspire by LinXueyuanStdio/LaTeX_OCR_PRO☆170Updated 4 years ago
- doc2x docs☆43Updated 2 months ago
- My implementation of Kosmos2.5 from the paper: "KOSMOS-2.5: A Multimodal Literate Model"☆71Updated this week
- A large scale camera-taken table detection and recognition dataset.☆118Updated last year
- This repo is used to release the ArxivFormula dataset.☆24Updated 2 months ago
- MPB (Miner-PDF-Benchmark) is an end-to-end PDF document comprehension evaluation suite designed for large-scale model data scenarios.☆20Updated last month
- [ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"☆213Updated last month
- ICDAR 2024 Table OCR Model☆28Updated last month