-
Hey, As others have mentioned before, your model works nicely with single-line text. Kudos for that! :tada:
I have been testing the pretrained handwritten model to recognize numbers, but it gets c…
-
I've used @bertsky's/ocrd_tesserocr's page_update_higher_textequiv_levels() in ocrd_calamari and now also in the WIP ocrd_trocr. Could this be included in core to avoid the copies?
-
Hey! Is there any way to finetune Tesseract models using PyTesseract? The current docs for finetuning on tesseract seem very hard to use and complicated, so it'd be very nice if PyTesseract could make…
-
请问“如果要训练识别多行文字，文字行之间可以加一个特殊字符标记，例如："1234\n4567\n89990"”是什么意思？是训练数据中需要用\n字符吗？
-
currently i am working on TR-OCR
MODEL USED- VisionEncoderDecoderModel
code -
/**
from PIL import Image
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
processor = TrOCRPro…
-
### Feature request
Hi, I'm one of the chinese developers that knows transformer.js by a Front End salon than invited transformer.js engineer to talk about this lib.
Now i'm going to work with clien…
-
I run the program in pycharm, one error listed below occurs, how to solve it?
ValueError: Unrecognized model in weights/icon_caption_florence. Should have a `model_type` key in its config.json, or co…
-
**Describe**
Model I am using (UniLM, MiniLM, LayoutLM ...):
unilm/trocr
-
- What is the best way to segment handwritten images into lines and extract corresponding text?
Related issues can be found here [line segmentation](https://stackoverflow.com/questions/75018081/ho…
-
**Describe**
I have taken checkout of commit **65f15af** and used model (trocr-large-stage1.pt) for text recognition.
Getting the below error:
ImportError: cannot import name 'TransformerDecoderLay…