PaddlePaddle/PP-FormulaNet_plus-L

Image To Text·PaddlePaddle· 14.5K· 5

PaddleOCR apache-2.0 Image To Text license:apache-2.0region:us

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull PaddlePaddle/PP-FormulaNet_plus-L

Model details

Task

Image To Text

Provider

PaddlePaddle

Framework

PaddleOCR

Size

694 MB

License

apache-2.0

Downloads

14.5K

Likes

Updated

2025-07-22

About PaddlePaddle/PP-FormulaNet_plus-L

PP-FormulaNetplus is an enhanced version of the formula recognition model developed by the PaddleOCR Team, building upon the original PP-FormulaNet. Compared to the original version, PP-FormulaNetplus utilizes a more diverse formula dataset during training, including sources such as Chinese dissertations, professional books, textbooks, exam papers, and mathematics journals. This expansion significantly improves the model’s recognition capabilities. The PP-FormulaNetplus includes multiple versions: L, M, and S, where PP-FormulaNetplus-L have added support for Chinese formulas and increased the maximum number of predicted tokens for formulas from 1,024 to 2,560, greatly enhancing the recognition performance for complex formulas. The key accuracy metrics are as follow:

Related Image To Text

B Salesforce/blip-image-captioning-base Image To Text 1.9M 863 🤗 HF B Salesforce/blip-image-captioning-large Image To Text ·469.7M params 737.4K 1.5K 🤗 HF P PaddlePaddle/PP-OCRv5_server_det Image To Text 587.3K 73 🤗 HF N numind/NuExtract3 Image To Text ·4.5B params 520.7K 270 🤗 HF U PaddlePaddle/UVDoc Image To Text 512.8K 11 🤗 HF T microsoft/trocr-small-handwritten Image To Text 448.6K 63 🤗 HF

Browse all Image To Text models →