khmer-trocr-base-printed

channudam/khmer-trocr-base-printed

khmer-trocr-base-printed is a image-text-to-text model from channudam. 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

3% of all-time downloads

All-time downloads

704

Public

Parameters

152M

8.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors608 MB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Aug 1, 2024
Updated: Aug 14, 2024
SHA: 570f68a9

Try a prompt

Model card

From the Hugging Face model README

khmer-trocr-base-printed

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

Loss: 0.0478
Cer: 0.4899

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: 4e-05
train_batch_size: 8
eval_batch_size: 6
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.0601	0.4876	1000	0.0793	0.5256
0.0467	0.9751	2000	0.0706	0.5147
0.0242	1.4627	3000	0.0658	0.5036
0.0206	1.9503	4000	0.0587	0.5083
0.0151	2.4378	5000	0.0610	0.5104
0.0127	2.9254	6000	0.0521	0.4912
0.0059	3.4130	7000	0.0497	0.4937
0.0045	3.9005	8000	0.0478	0.4899

Framework versions

Transformers 4.42.3
Pytorch 2.1.2
Datasets 2.20.0
Tokenizers 0.19.1

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
Created: Aug 1, 2024
Updated: Aug 14, 2024