llm-issue-bot[bot]
commented
10 months ago #
Issue Response
- ✨ Introduction: Thanks for opening this issue, I am the issue bot that will help you with your questoins!
- 🎯 First round response: The answer to your question is:
如果ppocr_keys_v1.txt字典里面不包含的字，比如“纡”，想要识别的话，需要按照以下步骤进行操作：
-
创建一个自定义字典文件，例如
custom_dict.txt，并将需要识别的字符逐行添加到文件中。在这种情况下，您可以将“纡”添加到custom_dict.txt中。 -
在配置文件中修改
character_dict_path参数，将其指向您创建的自定义字典文件路径。例如，将character_dict_path设置为ppocr/utils/dict/custom_dict.txt。 -
确保在配置文件中启用了识别空格的选项。您可以将
use_space_char设置为True，以便模型能够识别空格字符。
通过以上步骤，您可以使用自定义字典来识别字典中不存在的字符，如“纡”。
Relevant Sources
https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/applications/光功率计数码管字符识别/光功率计数码管字符识别.md, https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/deploy/lite/readme.md, https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.7/doc/doc_ch/recognition.md
How to use
My answer may not be accurate. I suggest you refer to relevant sources to make a comprehensive judgment. To invoke me for more questions, add a comment using following command: @llm-issue-bot \<QUESTION>
我们提供了issue bot来帮助你解答问题，你是否想要它来解答(请填写yes/no)?/We provide issue bot to solve issues, do you want it? (Please write yes/no):yes
请在这里描述你的问题/Please describe your issue here: 请问如果ppocr_keys_v1.txt字典里面不包含的字，比如“纡”，想要识别的话，需要怎么做