swinv2-ocr-finetuned-panjabi

HarsimarSingh/swinv2-ocr-finetuned-panjabi

swinv2-ocr-finetuned-panjabi is a image-text-to-text model from HarsimarSingh. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

6% of all-time downloads

All-time downloads

310

Public

Parameters

334M

56.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt2.7 GB · 50%

At a glance

Task: Image-Text-to-Text
Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Jan 3, 2025
Updated: Jan 10, 2025
SHA: 2e4560c5

Try a prompt

Model card

From the Hugging Face model README

swinv2-ocr-finetuned-panjabi

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.3457
Cer: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.8961	1.0	5883	1.6239	1.0
0.7295	2.0	11766	1.4693	1.0
0.5127	3.0	17649	1.4575	1.0
0.3661	4.0	23532	1.4469	1.0
0.3952	5.0	29415	1.4075	1.0
0.2733	6.0	35298	1.4193	1.0
0.1959	7.0	41181	1.3834	1.0
0.1422	8.0	47064	1.4467	1.0
0.0834	9.0	52947	1.3748	1.0
0.0703	10.0	58830	1.3457	1.0

Framework versions

Transformers 4.46.0
Pytorch 2.5.1+cu118
Datasets 2.20.0
Tokenizers 0.20.1

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
Created: Jan 3, 2025
Updated: Jan 10, 2025