Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型，仅20M参数量，可在浏览器中运行。训练全流程代码开源，以便自学复现。
| Date | Stars |
|---|---|
| 2026-07-24 | 873 |
| 2026-07-25 | 875 |
| 2026-07-28 | 874 |
| 2026-07-30 | 874 |
| 2026-08-06 | 874 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="center" style="margin-bottom: 0"> <img src="./assets/svg/logo-text.svg#gh-light-mode-only" alt="Texo Logo" width="300"/> <img src="./assets/svg/logo-text-dark.svg#gh-dark-mode-only" alt="Texo Logo" width="300"/> </p> <p align="center" style="font-size: 0.9em"> Texo is pronounced as /ˈtɛːkoʊ/ </p> <p align="center"> A minimalist free and open-source SOTA LaTeX OCR model which contains only 20M parameters. </p> <div align="center"> [Try it online](https://texocr.netlify.app) </div> <div align="center"> Technical report: [arXiv](https://arxiv.org/abs/2602.17189), [HAL](https://hal.science/hal-05510395) </div> ## Features - Free and open-source. - Fast and lightweight inference. - Trainable on consumer's-level GPU. - Well organized code as a tutorial. - [Running in browser!](https://github.com/alephpi/Texo-web) ## Prelude Despite a growing number of STEM and AI learners with their note-taking needs today, a free, fast, more accessible yet precise LaTeX OCR tool is still absent. Lying exactly in the comfort zone of machine learning due to the closed vocabulary and less generalization requirements, such classical pattern recognition task can be considered as solved thanks to recent deep learning progress(TrOCR, GOT-2.0, UniMERNet, PPFormulaNet). So here comes the Texo, which tackles this problem in the scope of a personal project. It is also a comprehensive practice to combine the knowledge and experiences I learned so far from school and online, as well as a tentative contribution to my beloved open source community. ## Performance Texo is a distilled version of PPFormulaNet-S and finetuned on UniMERNet-1M, hence it should preserve the most part of the performance compared to PPFormulaNet-S. Here is the evaluation results on the UniMERNet-Test dataset. | Model | Params | Metric | SPE | CPE | SCE | HWE | | :-------------------------------: | :--------------: | ------------- | ------ | ------ | ------ | ------ | | UniMERNet-T<sup>†</sup> | 107M | BLEU | 0.909 | 0.902 | 0.566 | 0.883 | | | | Edit distance | 0.066 | 0.075 | 0.239 | 0.078 | | PPFormulaNet-S<sup>†</sup> | 57M | BLEU | 0.8694 | 0.8071 | - | - | | | | Edit distance | - | - | - | - | | Texo-distill<sup>*</sup> | 20M | BLEU | 0.9014 | 0.8909 | 0.7034 | 0.8606 | | | | Edit distance | 0.0780 | 0.1042 | 0.1941 | 0.0995 | | Texo-transfer<sup>*</sup> | 20M<sup>**</sup> | BLEU | 0.8597 | 0.8334 | 0.5549 | 0.7973 | | | | Edit distance | 0.0980 | 0.1306 | 0.2187 | 0.0999 | | Texo-transfer-onnx | as above | BLEU | 0.8395 | 0.8136 | 0.5153 | 0.7787 | | | | Edit distance | 0.0980 | 0.1288 | 0.2050 | 0.0976 | We only list the lightweight version for the SOTA models, as we can see in terms of sequential metrics like BLEU or Edit distance, our model has comparable performance while reducing a lot of parameters. > `-` means not reported in the paper. > > †: Copy from the paper > > *: Texo-distill uses the same tokenizer as UniMERNet and PPFormulaNet, hence the sequential metrics are strictly comparable. While Texo-transfer uses a customized tokenizer hence the metrics are not comparable (we have a shorter sequence length, see more in [notes](./TechnoSelection/notes.md)). > > **: Slightly less than Texo-distill as the tokenizer's vocab is smaller. <img width="2035" height="480" alt="image" src="https://github.com/user-attachments/assets/273e115a-4bbf-4a0f-a3d5-54746c417fa7" /> ## Configure environment ```sh git clone https://github.com/alephpi/Texo uv sync
Excerpt of 8,626 characters
Read on GitHub
202
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:55fb11eb9d149ee3, topic:deep-learning, topic:pytorch
matched fp:55fb11eb9d149ee3, topic:ocr, desc:ocr, readme:ocr
matched fp:55fb11eb9d149ee3, topic:computer-vision