TrOCR_0219_All_data

yoon1000/TrOCR_0219_All_data

TrOCR_0219_All_data is a image-text-to-text model from yoon1000. 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

5% of all-time downloads

All-time downloads

191

Public

Parameters

385M

1.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.5 GB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Feb 19, 2024
Updated: Feb 19, 2024
SHA: 1abb2e6c

Try a prompt

Base models

microsoft/trocr-base-stage1

Model card

From the Hugging Face model README

TrOCR_0219_All_data

This model is a fine-tuned version of microsoft/trocr-base-stage1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.8182
Cer: 0.1603

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: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer
0.7188	0.05	500	0.8385	0.1740
0.9207	0.09	1000	0.8321	0.1692
1.1151	0.14	1500	0.8163	0.0989
0.9162	0.18	2000	0.6953	0.0830
0.5558	0.23	2500	0.8182	0.1603

Framework versions

Transformers 4.35.2
Pytorch 2.1.1+cu121
Datasets 2.13.0
Tokenizers 0.15.0

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
Created: Feb 19, 2024
Updated: Feb 19, 2024