alephpi / Texo
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。
Why this job: works in the areas we cover, but does not say which job it does
What it does
- Free and open-source.
- Fast and lightweight inference.
- Trainable on consumer's-level GPU.
- Well organized code as a tutorial.
- Running in browser!
Get started
# model only
python scripts/python/hf_hub.py pull You need: Mine: 50G CPU memory, A40/L40S 46G.; Recommend: 50G CPU memory, 40G GPU memory.; Minimal: 20G CPU memory(with streaming dataloading) and 16G GPU memory(with accumulative gradient).
- Maintenance
- Active
- Last commit 55 days ago
- Stars
- 919
- +3 this week
- Licence
- AGPL-3.0
- Share-alike, even hosted
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 95% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 2 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| robertknight / ocrs | 1,917 | 4 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 95%
- JavaScript 5%
- Shell <1%
Topics
- computer-vision
- deep-learning
- distillation-model
- hydra
- latex-ocr
- machine-learning
- python
- pytorch
- pytorch-lightning
- transformers
- formulanet
- unimernet
Project record
- JobOther AI tools
- StatusListed
- Commits209
- Forks56
- Watching4
- Stars in 28 days+13
- CreatedJul 29, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026