是否可以用大模型替代OCR呢？ #2331
yuruotong1
started this conversation in
Ideas
是否可以用大模型替代OCR呢？
#2331
Replies: 3 comments
-
|
可以参考Vary，GOT-OCR等工作，目前多模态大模不足的地方在于特殊场景以及会漏 |
Beta Was this translation helpful? Give feedback.
0 replies
-
GOT-OCR 效果跟qwen2.5 VL 系列相比 效果如何 您这边有测试过吗 |
Beta Was this translation helpful? Give feedback.
0 replies
-
在我们场景下会漏检，直接pass了 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
我看现在的翻译工作多是基于本地模型的OCR，我在magic-pdf中配置了llm-aided-config，但貌似还是用的本地模型，我如何使用大模型完成识别呢？
之所以想用大模型，是因为我想自定义翻译的效果，比如能够定制一些专业词汇、增加一些活泼的气氛等等
Beta Was this translation helpful? Give feedback.
All reactions