Create app.py

app.py

@@ -0,0 +1,48 @@
+# app.py
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+from PIL import Image
+import numpy as np
+
+# Load model and tokenizer
+tokenizer = AutoTokenizer.from_pretrained("microsoft/trocr-base-handwritten")
+model = AutoModelForTokenClassification.from_pretrained("microsoft/trocr-base-handwritten")
+
+# Create OCR pipeline
+ocr_pipeline = pipeline(
+    "image-to-text",
+    model=model,
+    tokenizer=tokenizer,
+    feature_extractor=tokenizer.init_feature_extractor()
+)
+
+def predict_handwriting(image):
+    """
+    Function to process handwritten text image and return transcription
+    """
+    try:
+        # Preprocess image
+        image = image.convert("RGB")
+        image = np.array(image)
+        
+        # Run OCR
+        result = ocr_pipeline(image)
+        
+        # Extract text from results
+        transcription = " ".join([word["value"] for word in result])
+        return transcription
+    
+    except Exception as e:
+        return f"Error processing image: {str(e)}"
+
+# Create Gradio interface
+demo = gr.Interface(
+    fn=predict_handwriting,
+    inputs=gr.Image(type="pil", label="Upload Handwritten Text Image"),
+    outputs=gr.Textbox(label="Transcription"),
+    title="Handwritten Text to Text Converter",
+    description="Upload a handwritten text image and get the transcribed text. Best results with clear, high-contrast images."
+)
+
+if __name__ == "__main__":
+    demo.launch()