-
Thanks for your brilliant work! That's helped me a lot!
And I would like to know if there is a simple way to extract the raw words from the result image, since I have a .pdf format file which include…
-
在输入同样的图片的时，几次测试结果不一致，时好时坏，请问是什么原因导致的呢？有什么方法可以使结果稳定吗？
-
-
## 问题描述
使用OpenAI翻译，身份验证正常，使用`git-4o-mini`模型翻译后，进度条正常走完，但报错：
```
Executing command: cd "R:\Temp\tmpu5gmxg3g" && pdf2zh "R:\Temp\tmpu5gmxg3g\input.pdf" -lo zh -s openai:gpt-4o-mini -p 1
Files in …
-
I have scanned documents, pictures of document taken by phone etc. where first I need to detect single page to eliminate rest of image or fix rotation. Is it possible to extend a model by such a featu…
-
## 问题描述
请对问题进行描述，并提供日志或截图
**本项目不处理网络环境引发的问题**（例如 Empty translation result/Connection reset）
D:\>set DEEPL_SERVER_URL=https://deeplx.papercar.top/translate
(para) D:\>pdf2zh geo.pdf -s deepl
C:…
-
ckpt = torch.load(file, map_location="cpu")
1%|█ | 8/583 [00:04
-
return ssl_context.wrap_socket(sock)
File "D:\ProgramData\Anaconda3\lib\ssl.py", line 500, in wrap_socket
return self.sslsocket_class._create(
File "D:\ProgramData\Anaconda3\lib\ssl.py"…
-
我们尝试了大概50份文件，发现了一些存在的现象：
1、存在信息内容粘连情况。换行、空格等识别效果不太好
2、复杂结构容易出现内容错乱情况，比如左右结构的文档，比如：
文件内容：
识别后模块：
![image]…
-
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File "C:\anaconda\envs\ppp\Scripts\pdf2zh.exe\__main__.py", line 7, in
File "C:…