Update app.py

app.py

@@ -1,34 +1,52 @@
 import gradio as gr
-from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 from PIL import Image
-import numpy as np
+import requests
+import torch
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+import logging
+
+# Setup logging
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
 
-# Load the model and processor
-processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-handwritten')
-model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-handwritten')
+# Load processor and model
+model_name = "microsoft/trocr-large-handwritten"
+processor = TrOCRProcessor.from_pretrained(model_name)
+model = VisionEncoderDecoderModel.from_pretrained(model_name)
 
-# Define the prediction function
+# Function to recognize handwriting
 def recognize_handwriting(image):
-    if isinstance(image, dict):
-        image = Image.fromarray(image['image'])
-    elif isinstance(image, np.ndarray):
-        image = Image.fromarray(image)
-    else:
-        image = Image.open(image)
+    try:
+        logger.info("Received an image for handwriting recognition.")
+        if isinstance(image, dict):
+            image = image.get("image")
+        
+        if image is None:
+            logger.error("No image found in the input.")
+            return "No image found"
 
-    pixel_values = processor(image, return_tensors="pt").pixel_values
-    generated_ids = model.generate(pixel_values)
-    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    return generated_text
+        image = Image.fromarray(image).convert("RGB")
+        pixel_values = processor(images=image, return_tensors="pt").pixel_values
+        generated_ids = model.generate(pixel_values)
+        generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+        logger.info("Handwriting recognized successfully.")
+        return generated_text
+    except Exception as e:
+        logger.error(f"Error during handwriting recognition: {e}")
+        return f"Error: {str(e)}"
 
-# Create the Gradio interface
-image_input = gr.Sketchpad(label="Draw or Upload an Image")
-output_text = gr.Textbox(label="Recognized Text")
+# Create Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("## Handwritten Text Recognition")
+    with gr.Row():
+        with gr.Column():
+            image_input = gr.Image(tool="editor", type="numpy", label="Draw or Upload an Image")
+            submit_button = gr.Button("Submit")
+        with gr.Column():
+            output_text = gr.Textbox(label="Recognized Text")
+    
+    submit_button.click(fn=recognize_handwriting, inputs=image_input, outputs=output_text)
 
-gr.Interface(
-    fn=recognize_handwriting,
-    inputs=image_input,
-    outputs=output_text,
-    title="Handwritten Text Recognition",
-    description="Draw or upload an image of handwritten text to recognize it.",
-).launch()
+# Launch the app
+if __name__ == "__main__":
+    demo.launch()