| license: cc-by-sa-4.0 | |
| # Ocrs pre-trained models | |
| Pre-trained models for the [Ocrs](https://github.com/robertknight/ocrs) OCR engine project. | |
| This includes text detection and recognition models available as: | |
| - PyTorch checkpoints | |
| - ONNX models | |
| - [RTen](https://github.com/robertknight/rten) models | |
| Training and evaluation scripts and documentation can be found in the [ocrs-models](https://github.com/robertknight/ocrs-models) repository. | |
| ## Datasets | |
| Models are trained on [HierText](https://github.com/google-research-datasets/hiertext) and synthetic data. |