中英文混合的图片无法识别英文之间的空格 #13200
Replies: 3 comments 4 replies
-
|
这个我之前也发现了。应该是中英文混合训练数据较少导致模型识别效果不太行 |
Beta Was this translation helpful? Give feedback.
-
|
在自己的场景下，再训练一下。 |
Beta Was this translation helpful? Give feedback.
-
|
离谱啊，我只是一个使用者，不懂ocr，一个这么牛逼的库，竟然不支持中英文混合，吐血。。 |
Beta Was this translation helpful? Give feedback.
-
|
你的图是啥样的，能共享几张吗 |
Beta Was this translation helpful? Give feedback.
-
|
随便一个截图，包含中英文，用默认的模型都识别不了 |
Beta Was this translation helpful? Give feedback.
-
|
有什么办法，通过调整参数支持i一下空格吗？我主要是一张图片里面都有中文和英文，英文不多，但是不能没有空格，其次批量处理的时候，有可能是中文图片也可能是英文图片。 主要是产出数据给多模态训练，paddleocr为啥不支持中英文混合，比较原始啊 |
Beta Was this translation helpful? Give feedback.
-
|
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
设置了use_space_char依旧无效，v4模型。
Beta Was this translation helpful? Give feedback.
All reactions