Update app.py

app.py

@@ -1,67 +1,41 @@
-import cv2
-from pytesseract import pytesseract
-from transformers import AutoModel, AutoTokenizer
 import gradio as gr
+import torch
+import pytesseract
+from transformers import AutoTokenizer, AutoModel
 
-# Model and Tesseract Configuration
-# Load GOT2 model for English text and configure Tesseract for Hindi text
-tokenizer_eng = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
-model_eng = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True, device_map='cpu').eval()
-
-# Define Tesseract path and configuration for Hindi
-pytesseract.tesseract_cmd = '/usr/bin/tesseract'
-tesseract_config = '--oem 3 --psm 6 -l hin'
-
-# Perform OCR function
-def perform_ocr(img, language):
-    img_path = "/tmp/uploaded_image.png"
-    img.save(img_path)
-
-    res_eng = ""
-    res_hin = ""
-
-    if language in ["English", "Both"]:
-        res_eng = model_eng.chat(tokenizer_eng, img_path, ocr_type='ocr')
-
-    if language in ["Hindi", "Both"]:
-        img_cv = cv2.imread(img_path)
-        res_hin = pytesseract.image_to_string(img_cv, config=tesseract_config)
-
-    return res_eng, res_hin
-
-# Keyword Search Functionality
-def ocr_and_search(image, language, keyword):
-    english_text, hindi_text = perform_ocr(image, language)
+pytesseract.pytesseract.tesseract_cmd = r'/opt/homebrew/bin/tesseract'
 
-    extracted_english = f"Extracted English Text:\n{english_text}" if english_text else "No English text extracted."
-    extracted_hindi = f"Extracted Hindi Text:\n{hindi_text}" if hindi_text else "No Hindi text extracted."
-
-    # Search for the keyword in the extracted text
-    search_results = []
-    if keyword:
-        if language in ["English", "Both"] and keyword.lower() in english_text.lower():
-            search_results.append(f"Keyword '{keyword}' found in English text.")
-
-        if language in ["Hindi", "Both"] and keyword.lower() in hindi_text.lower():
-            search_results.append(f"Keyword '{keyword}' found in Hindi text.")
-
-    search_output = "\n".join(search_results) if search_results else "No matches found."
-
-    return extracted_english, extracted_hindi, search_output
-
-# Gradio Interface Setup
-with gr.Blocks() as app:
-    gr.Markdown("### OCR Application")
-    image_input = gr.Image(type="pil", label="Upload Image")
-    language_selection = gr.Radio(choices=["English", "Hindi", "Both"], label="Select Language")
-    keyword_input = gr.Textbox(placeholder="Enter keyword to search", label="Keyword Search")
-    output_english = gr.Textbox(label="Extracted English Text", interactive=False)
-    output_hindi = gr.Textbox(label="Extracted Hindi Text", interactive=False)
-    output_search = gr.Textbox(label="Search Results", interactive=False)
-
-    submit_button = gr.Button("Submit")
-    submit_button.click(fn=ocr_and_search, inputs=[image_input, language_selection, keyword_input], outputs=[output_english, output_hindi, output_search])
-
-# Application Launch
+# Load the tokenizer and model
+tokenizer_eng = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
+model_eng = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True).eval()
+
+def perform_ocr(image, language):
+    # Perform OCR for English
+    img_cv = image  # Assuming image is already in the correct format
+    res_eng = model_eng.chat(tokenizer_eng, img_cv, ocr_type='ocr')
+
+    return res_eng  # Return results for English
+
+def ocr_and_search(image, language):
+    # Call the perform_ocr function
+    english_text = perform_ocr(image, language)
+    # You may also want to implement any searching functionality here
+    # ...
+    
+    return english_text  # Return the OCR result for English
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=ocr_and_search,
+    inputs=[
+        gr.Image(type="numpy", label="Upload Image"),
+        gr.Dropdown(choices=["English", "Hindi"], label="Select Language")
+    ],
+    outputs=gr.Textbox(label="Extracted Text"),
+    title="OCR Application",
+    description="Upload an image to extract text using OCR."
+)
+
+# Run the app
 if __name__ == "__main__":
-    app.launch()
+    iface.launch()