korean_mobile_rec / README.md
ProtenLabs's picture
Update README.md
ce4b34b verified
|
Raw
History Blame Contribute Delete
930 Bytes
---
base_model:
- PaddlePaddle/PP-OCRv5_mobile_rec
---
# PP-OCRv5 Mobile Fine-Tuned Text Recognition Model
This model is a fine-tuned `PP-OCRv5_mobile_rec` model for recognizing text in table documents.
## Fine-Tuning Details
- Base model: `PP-OCRv5_mobile_rec`
- Task: Text recognition in table documents
- Data type: Image
- File format: TXT
- Training data: 303,176 examples
- Data size: 2.0 GB
- Epochs: 20
## Evaluation
| Metric | Before | After |
| --- | ---: | ---: |
| Accuracy | 0.7271126734960821 | 0.8616197152759869 |
## Government R&D Project
This software is a result of the following government research and development project:
| Item | Details |
|------|---------|
| Project Name | AI ๊ธฐ๋ฐ˜ ์ค‘์†Œ๊ธฐ์—… ์—…๋ฌด ์ž๋™ํ™” ๋ฐ ํ†ตํ•ฉ ๊ฒ€์ƒ‰ ์†”๋ฃจ์…˜ |
| Project No. | RQT-25-090153 |
| Supervisor | ์ •๋ณดํ†ต์‹ ์‚ฐ์—…์ง„ํฅ์› |
| Performer | Proten Co., Ltd. |
| R&D Period | 2026.01.01 ~ 2026.06.30 |