Instructions to use Yaredoffice/geez-char-ocr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Yaredoffice/geez-char-ocr with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://Yaredoffice/geez-char-ocr") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signature58df1c9
-
Update README.md
Verified signaturec6be04e -
Update README.md
Verified signatureGeez-Net is designed to convert images of handwritten Geez characters into their corresponding text labels. It addresses the challenge of limited datasets by utilizing a hybrid training strategy involving aggressive geometric and photometric augmentation (Zoom, Shift, Brightness, Contrast). The model is particularly effective in scenarios involving: Digitizing handwritten notes. Educational applications for language learning. Pre-processing document datasets.bef22fb -
Upload folder using huggingface_hub
Verified signaturefdf6f8c -
initial commit
Verified signature12d21a0