trocr-finetuned

fjfur10/trocr-finetuned

trocr-finetuned is a image-text-to-text model from fjfur10. 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

17% of all-time downloads

All-time downloads

Public

Parameters

61.6M

1.5 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors246 MB · 100%

At a glance

Task: Image-Text-to-Text
Library: transformers
Model type: vision-encoder-decoder
Access: Public
Created: Oct 31, 2024
Updated: Dec 2, 2024
SHA: b97e51a6

Try a prompt

Base models

microsoft/trocr-small-stage1

Model card

From the Hugging Face model README

trocr-finetuned

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

Loss: 9.2627
Cer: 0.5872
Wer: 1.0264

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-07
train_batch_size: 6
eval_batch_size: 6
seed: 42
optimizer: Use 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: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Cer	Wer
13.1378	1.0	50	9.7690	0.6655	1.2093
12.3944	2.0	100	9.4940	0.6319	1.1423
12.4749	3.0	150	9.3537	0.5940	1.0691
10.9977	4.0	200	9.2874	0.5884	1.0427
10.8077	5.0	250	9.2627	0.5872	1.0264

Framework versions

Transformers 4.46.2
Pytorch 2.5.1+cu121
Datasets 3.1.0
Tokenizers 0.20.3

Task: Image-Text-to-Text
Library: transformers
Type: vision-encoder-decoder
Created: Oct 31, 2024
Updated: Dec 2, 2024