Upload README.md with huggingface_hub

README.md

@@ -6,11 +6,13 @@ tags:
 - arabic
 - keras
 - jax
+- tensorflow
+- pytorch
 ---
 
 # Qalam-Net (قلم-نت): Advanced Arabic OCR
 
-Qalam-Net is a high-performance, cross-backend Optical Character Recognition (OCR) model for Arabic. Built on **Keras 3**, it supports **JAX**, **PyTorch**, and **TensorFlow** backends.
+Qalam-Net is a high-performance, cross-backend Optical Character Recognition (OCR) model for Arabic. Built on **Keras 3**, it supports **JAX**, **PyTorch**, and **TensorFlow** backends for seamless deployment across any infrastructure.
 
 ## 🚀 Quick Start (Advanced Usage)
 
@@ -24,36 +26,32 @@ pip install -U "keras>=3.0" jax jaxlib huggingface_hub opencv-python
 ### 2. Implementation
 ```python
 import os
-os.environ["KERAS_BACKEND"] = "jax" # Options: "jax", "tensorflow", "torch"
+os.environ["KERAS_BACKEND"] = "jax" # Switch to "tensorflow" or "torch" if preferred
 
 import keras
 import numpy as np
 import cv2
+from huggingface_hub import hf_hub_download
 
 class QalamNet:
     def __init__(self, repo_id="Ali0044/Qalam-Net"):
-        # Download and load the latest model using the hf:// shorthand
-        # This automatically downloads the model.keras file from the root of the repo
-        self.model = keras.saving.load_model(f"hf://{repo_id}")
+        # Download and load the latest model from Hugging Face
+        print(f"Fetching model from {repo_id}...")
+        model_path = hf_hub_download(repo_id=repo_id, filename="model.keras")
+        self.model = keras.saving.load_model(model_path)
         
-        # Standard Arabic Vocabulary (Matches training set)
+        # Standard Arabic Vocabulary
         self.vocab = [' ', '!', '"', '#', '(', ')', '*', '+', ',', '-', '.', '/', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', ':', ';', '=', '?', '[', ']', 'ء', 'آ', 'أ', 'ؤ', 'إ', 'ئ', 'ا', 'ب', 'ة', 'ت', 'ث', 'ج', 'ح', 'خ', 'د', 'ذ', 'ر', 'ز', 'س', 'ش', 'ص', 'ض', 'ط', 'ظ', 'ع', 'غ', 'ـ', 'ف', 'ق', 'ك', 'ل', 'م', 'ن', 'ه', 'و', 'ى', 'ي', 'ً', 'ٌ', 'ٍ', 'َ', 'ُ', 'ِ', 'ّ', 'ْ', '٠', '١', '٢', '٣', '٤', '٥', '٦', '٧', '٨', '٩']
         
     def preprocess(self, image_path):
-        # 1. Load as grayscale
         img = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
-        # 2. Resize to 128 (width) x 32 (height)
         img = cv2.resize(img, (128, 32))
-        # 3. Normalize
         img = (img / 255.0).astype(np.float32)
-        # 4. Transpose (W, H) -> (H, W) for CRNN processing
         img = img.T
-        # 5. Expand dimensions for batch and channel
         img = np.expand_dims(img, axis=-1)
         return np.expand_dims(img, axis=0)
 
     def predict(self, image_path):
-        # Run inference
         batch_img = self.preprocess(image_path)
         predictions = self.model.predict(batch_img)
         
@@ -62,26 +60,20 @@ class QalamNet:
         results = keras.backend.ctc_decode(predictions, input_length=input_len, greedy=True)[0][0]
         
         # Map indices to characters
-        text = ""
-        for res in results[0]:
-            if res != -1:
-                text += self.vocab[int(res)]
+        text = "".join([self.vocab[int(res)] for res in results[0] if res != -1])
         return text
 
-# Initialize
-ocr = QalamNet()
-
-# Predict
-# text = ocr.predict("sample_arabic_text.png")
-# print(f"Predicted Text: {text}")
+# Usage
+# ocr = QalamNet()
+# print(f"Predicted: {ocr.predict('image.png')}")
 ```
 
 ## 🧠 Model Architecture
 Qalam-Net employs a specialized **CNN-BiLSTM-Attention** pipeline:
-- **Spatial Features**: 3-block CNN with BatchNormalization.
-- **Sequence Context**: Stacked Bidirectional LSTMs.
-- **Focus Mechanism**: Self-attention layer to resolve overlapping Arabic characters.
-- **Loss**: Trained using Connectionist Temporal Classification (CTC).
+- **Spatial Features**: 3-block CNN for robust feature extraction.
+- **Sequence Context**: Dual Bidirectional LSTMs to capture Arabic script flow.
+- **Focus Mechanism**: Self-attention layer for character-level precision.
+- **Decoding**: Connectionist Temporal Classification (CTC).
 
 ---
 **Developed by [Ali Khalid](https://github.com/Ali0044)**