Update app.py

app.py

@@ -1,69 +1,32 @@
 import gradio as gr
-import torch
-from PIL import Image
 from transformers import TrOCRProcessor, VisionEncoderDecoderModel
-import os
-import json
-
-# Load the model and processor
-processor = TrOCRProcessor.from_pretrained('microsoft/trocr-base-handwritten')
-model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-base-handwritten')
-
-# Handle model initialization warnings
-model.eval()
+from PIL import Image
+import numpy as np
 
-# Load feedback data
-feedback_data_path = "feedback_data.json"
-if os.path.exists(feedback_data_path):
-    with open(feedback_data_path, "r") as file:
-        feedback_data = json.load(file)
-else:
-    feedback_data = []
+# Load the processor and model
+processor = TrOCRProcessor.from_pretrained('microsoft/trocr-large-handwritten')
+model = VisionEncoderDecoderModel.from_pretrained('microsoft/trocr-large-handwritten')
 
 def recognize_handwriting(image):
     if isinstance(image, dict):
-        image = Image.fromarray(image['image'].astype('uint8')).convert("RGB")
-    else:
-        image = Image.open(image).convert("RGB")
-
-    pixel_values = processor(images=image, return_tensors="pt").pixel_values
+        image = image["image"]
+    pil_image = Image.fromarray(image).convert("RGB")
+    pixel_values = processor(images=pil_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
 
-def provide_feedback(image, corrected_text):
-    feedback_data.append({
-        "image": image,
-        "corrected_text": corrected_text
-    })
-    
-    # Save feedback every 5 entries
-    if len(feedback_data) % 5 == 0:
-        with open(feedback_data_path, "w") as file:
-            json.dump(feedback_data, file)
-    
-    return "Feedback received. Thank you!"
+# Gradio interface
+image_input = gr.Image(tool="editor", type="numpy", label="Draw or Upload an Image")
+output_text = gr.Textbox(label="Recognized Text")
 
-# Gradio Interface
-with gr.Blocks() as demo:
-    gr.Markdown("# Handwriting Recognition with Feedback")
-    
-    with gr.Tabs():
-        with gr.TabItem("Recognize Handwriting"):
-            image_input = gr.Image(source="upload", tool="editor", type="numpy", label="Draw or Upload an Image")
-            recognize_button = gr.Button("Recognize Handwriting")
-            output_text = gr.Textbox(label="Recognized Text")
-            
-            recognize_button.click(recognize_handwriting, inputs=image_input, outputs=output_text)
-        
-        with gr.TabItem("Provide Feedback"):
-            feedback_image_input = gr.Image(source="upload", tool="editor", type="numpy", label="Draw or Upload an Image")
-            corrected_text_input = gr.Textbox(label="Corrected Text")
-            feedback_button = gr.Button("Submit Feedback")
-            feedback_output = gr.Textbox(label="Feedback Status")
-            
-            feedback_button.click(provide_feedback, inputs=[feedback_image_input, corrected_text_input], outputs=feedback_output)
+iface = gr.Interface(
+    fn=recognize_handwriting,
+    inputs=image_input,
+    outputs=output_text,
+    title="Handwriting Recognition",
+    description="Draw or upload an image of handwritten text, and the model will recognize the text.",
+    live=True,
+)
 
-# Run the Gradio app
-demo.launch(share=True)
+iface.launch()