Brian314/TexTeller
By Brian314 · ↓ 2 · ♥ 1 · Updated 2024-08-14
What's in this repo
This page lists the files in Brian314/TexTeller, including decoder_model.onnx, decoder_model_merged.onnx, decoder_with_past_model.onnx and more.
- 4 ONNX models (.onnx files)
- 17 files, including 7 .json, 4 .onnx, 2 .md, 1 .txt, 1 .safetensors, 1 .bin
- Last updated 2024-08-14
ONNX files
| File | Size | Download |
|---|---|---|
| decoder_model.onnx | — | Download |
| decoder_model_merged.onnx | — | Download |
| decoder_with_past_model.onnx | — | Download |
| encoder_model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
About TexTeller
- 📮[2024-03-25] TexTeller 2.0 released! The training data for TexTeller 2.0 has been increased to 7.5M (about 15 times more than TexTeller 1.0 and also improved in data quality). The trained TexTeller 2.0 demonstrated superior performance in the test set, especially in recognizing rare symbols, complex multi-line formulas, and matrices.
There are more test images here and a horizontal comparison of recognition models from different companies.
TexTeller is a ViT-based model designed for end-to-end formula recognition. It can recognize formulas in natural images and convert them into LaTeX-style formulas.
TexTeller is trained on a larger dataset of image-formula pairs (a 550K dataset available here), exhibits superior generalization ability and higher accuracy compared to LaTeX-OCR, which uses approximately 100K data points. This larger dataset enables TexTeller to cover most usage scenarios more effectively.
For more details, please refer to the 𝐓𝐞𝐱𝐓𝐞𝐥𝐥𝐞𝐫 GitHub repository.
Model info
Created: 2024-08-14
Updated: 2024-08-14
View on Hugging Face