breezedeus/Pix2Text
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.
Jupyter NotebookMIT
Issues
- 3
使用GPU比cpu还慢
#161 opened by bearmeetu - 0
如何将pdf的图片不要进行ocr识别
#160 opened by Zhengyu-Ju - 6
1.1.2使用报错
#158 opened by xuanyucode - 1
我想打包成exe,有什么最佳实践吗,现在打包后运行报错,需要在代码里指定模型路径吗?
#154 opened by xuanyucode - 1
是不是有python 版本要求, python3.13 安装报错
#157 opened by vvvli1 - 3
error install
#156 opened by nvha63 - 2
在运行的时候,内存使用越来越大,导致最后的OOM,请问有什么解决办法吗,我是单进程跑的
#155 opened by lvzhaokun - 1
关于生成LaTeX的公式的可读性问题
#136 opened by realDGD - 1
可不可以直接使用代码运行
#137 opened by 2257396011 - 1
找不到转换后文件的存储路径呢
#139 opened by orcharddd1990 - 1
Couldn't connect to server
#147 opened by xiaoxstz - 1
CoreML integration
#150 opened by DwarfCommunist - 1
不同公式识别时间差异大正常吗?
#151 opened by 520jefferson - 3
识别时间过长,如何优化
#149 opened by 520jefferson - 2
Multilingual not working?
#148 opened by Maissan26 - 3
Mathematical proofs in ArXiv papers recognized by OCR have appeared with irrelevant Chinese.
#142 opened by bwnjnOEI - 4
本地推理效果和huggingface demo不一样
#145 opened by TideDra - 2
Spanish options
#146 opened by AlonsoFU - 0
- 2
怎么样进行模型的训练
#143 opened by Linjiehua - 1
线上部署pix2text,有几个问题
#141 opened by orcharddd1990 - 0
下边应该是正常启动成功了吧,但是访问http://0.0.0.0:8503/,报502错误,用自带的try_service.py调试时,requests.post(url, data=data, files=files)报502,这是啥原因呢?
#138 opened by orcharddd1990 - 6
求助:使用无法使用cuda加速
#121 opened by meng0423 - 2
公式识别为False时报错。
#129 opened by wertyac - 1
ValueError: The truth value of an array with more than one element is ambiguous. Use a.any() or a.all()
#135 opened by Espacio-root - 3
配置layout_parser时在config中传入root在方法中报错
#116 opened by AILock - 2
关于模型评估过程中的标准化操作
#104 opened by Sanster - 2
- 3
Poor accuracy when trying to run inference on single and short expressions
#95 opened by BrianPark314 - 2
开源模型无法识别斜的场景
#110 opened by evanlin88 - 1
可否告知免费版模型训练数据量级
#89 opened by ManiiXu - 5
列表索引超出范围 是什么原因呢?
#111 opened by Metasymbols - 1
- 0
one more problem i saw is that the text output is different if I use raw easyocr and your pix2tex.recognize_text_formula
#133 opened by KTBsomen - 3
why useing the cnOCR it's not accurate as you are using easyocr then it is fine
#130 opened by KTBsomen - 1
Unable to use GPU / CUDA for prediction
#132 opened by breezyChedi - 1
希望增加网页版一键复制公式进word的操作
#131 opened by Cyan2077 - 1
- 2
- 3
ParseError
#91 opened by hl-gl - 1
公式图片的背景色是透明色,无法识别公式
#102 opened by evanlin88 - 3
示例运行显示错误, 无法下载p2t-mfr-onnx.zip模型
#90 opened by lk1983823 - 1
可以添加文档识别功能
#77 opened by zsy1207 - 1
Index out of bounds when merging text
#86 opened by tonyzdev - 1
YoloV7_Tiny 自动下载失败
#87 opened by xiehurricane - 2
在非root用户,用systemctl自动启动p2t serve会出现[Errno 13] Permission denied: 'output-md-root'
#101 opened by realDGD - 3
- 7
- 1
加载不到插件
#83 opened by xjq9426586 - 9