How to fine-tune PaddleOCR-VL on custom dataset #16672
Replies: 2 comments 3 replies
-
|
Exactly it has some issues in which language it was trained on. How many docs we need, the format and resources related stuff. This will be really helpful for all. |
Beta Was this translation helpful? Give feedback.
-
|
Hello, we completely understand your needs. Support for fine-tuning is currently in progress! The PaddleOCR-VL-0.9B model will soon support training and fine-tuning in the ERNIEKit repository, and there will be detailed documentation. Please stay tuned for updates. |
Beta Was this translation helpful? Give feedback.
-
|
Eagerly waiting! Also please share the link to the repo, so that we can subscribe. |
Beta Was this translation helpful? Give feedback.
-
|
This feature will be supported soon. Please stay tuned! |
Beta Was this translation helpful? Give feedback.
-
|
Our team has also encountered a problem that requires fine-tuning. If the document comes out, can we share this link? Thank you very much.
|
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello,
is it possible to fine-tune PaddleOCR-VL on a custom dataset?
If yes, could you please share some guidance or documentation about how to do it?
I would like to fine-tune the model on my own dataset, but the documentation does not provide clear steps.
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions