metadata
license: cc-by-sa-4.0
Ocrs pre-trained models
Pre-trained models for the Ocrs OCR engine project.
This includes text detection and recognition models available as:
- PyTorch checkpoints
- ONNX models
- RTen models
Training and evaluation scripts and documentation can be found in the ocrs-models repository.
Datasets
Models are trained on HierText and synthetic data.