Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

中文md文件,后半部分公式识别有问题 #299

Open
narutojxl opened this issue Aug 31, 2024 · 2 comments
Open

中文md文件,后半部分公式识别有问题 #299

narutojxl opened this issue Aug 31, 2024 · 2 comments

Comments

@narutojxl
Copy link

narutojxl commented Aug 31, 2024

作者您好,感谢开源这么好的工具,刚支持了一点点心意。
论文:Vehicle-Motion-Constraint-Based_Visual-Inertial-Odometer_Fusion_With_Online_Extrinsic_Calibration_compressed.pdf

问题复现:

  1. 上传离线paper pdf;
  2. 当前模型:siliconflow-THUDM/glm-4-9b-chat

image

  1. 下载 翻译后的带图文档-可用于手动修正-需要vscode.zip

这是结果中,英文paper的md文件, 0191a6fc-8dfb-73d1-9aac-2aa968c488b6_md.md,其中把一些文本误识别成了图片,但是公式看起来都是对的。 这是中文md文件,translated_markdown.md, 从公式17开始就识别有问题了。

中间有几次一直提示“DOC2X服务不可用,现在将执行效果稍差的旧版代码。”, 换了模型类型: 硅基流动的Yi-1.5-9B和glm4-9b,yi-34b和qwen-110b 都不行。 DOC2X 现在网页服务暂停,需要到9月中旬左右恢复, 本来想尝试 “自己去Doc2X网站去转换,下载md的压缩包,解压后,只用把里面的md文件在我的网站做翻译,这时候只用选择“Markdown英译中(记得看上面的教程3!)”即可。”, 但是没法测试。

@narutojxl
Copy link
Author

I don't understand why this problem fix need to install this app

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants
@narutojxl and others