Finetuned model availability for document parsing(OCR) or Key Information Extraction
#3
by stray-light - opened
The original paper mentions good performance on FUNSD text parsing "where Mask R-CNN is used with different backbones
(ResNeXt, DeiT, BEiT, MAE and DiT)" . Is the finetuned model available on Huggingface? How to fine-tune for my own task?