robertknight
commited on
Add initial project README
Browse files
README.md
CHANGED
@@ -1,3 +1,19 @@
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: cc-by-sa-4.0
|
3 |
---
|
4 |
+
|
5 |
+
# Ocrs pre-trained models
|
6 |
+
|
7 |
+
Pre-trained models for the [Ocrs](https://github.com/robertknight/ocrs) OCR engine project.
|
8 |
+
|
9 |
+
This includes text detection and recognition models available as:
|
10 |
+
|
11 |
+
- PyTorch checkpoints
|
12 |
+
- ONNX models
|
13 |
+
- [RTen](https://github.com/robertknight/rten) models
|
14 |
+
|
15 |
+
Training and evaluation scripts and documentation can be found in the [ocrs-models](https://github.com/robertknight/ocrs-models) repository.
|
16 |
+
|
17 |
+
## Datasets
|
18 |
+
|
19 |
+
Models are trained on [HierText](https://github.com/google-research-datasets/hiertext) and synthetic data.
|