trocr-small-korean

team-lucid/trocr-small-korean

trocr-small-korean is a image-to-text model from team-lucid. Use it when you need a caption or text from an image. It is set up for transformers. The card lists the license as apache-2.0.

TrOCR은 Encoder-Decoder 모델로, 이미지 트랜스포머 인코더와 텍스트 트랜스포머 디코더로 이루어져 있습니다. 이미지 인코더는 DeiT 가중치로 초기화되었고, 텍스트 디코더는 자체적으로 학습한 RoBERTa 가중치로 초기화되었습니다.

Downloads · 30 days

7.7K

9% of all-time downloads

All-time downloads

88.8K

Public

Parameters

54.5M

655 MB on disk

Likes

Trending 1

Hugging Face

Repo makeup

Click a slice to open those files.

.bin218 MB · 33%

At a glance

Task: Image-to-Text
Library: transformers
License: apache-2.0
Model type: vision-encoder-decoder
Access: Public
Created: Jun 30, 2023
Updated: Jul 1, 2023
SHA: 33e0a37b

Spaces

Model card

From the Hugging Face model README

trocr-small-korean

Model Details

이 연구는 구글의 TPU Research Cloud(TRC)를 통해 지원받은 Cloud TPU로 학습되었습니다.

How to Get Started with the Model

import torch

from transformers import VisionEncoderDecoderModel

model = VisionEncoderDecoderModel.from_pretrained("team-lucid/trocr-small-korean")

pixel_values = torch.rand(1, 3, 384, 384)
generated_ids = model.generate(pixel_values)

Training Details

Training Data

해당 모델은 synthtiger로 합성된 6M개의 이미지로 학습되었습니다

Training Hyperparameters

Hyperparameter	Small
Warmup Steps	4,000
Learning Rates	1e-4
Batch Size	512
Weight Decay	0.01
Max Steps	500,000
Learning Rate Decay	0.1
\(Adam\beta_1\)	0.9
\(Adam\beta_2\)	0.98

Task: Image-to-Text
Library: transformers
Type: vision-encoder-decoder
License: apache-2.0
Languages: ko
Created: Jun 30, 2023
Updated: Jul 1, 2023