Update app.py

app.py

@@ -6,10 +6,9 @@ from PIL import Image, ImageDraw, ImageFont
 
 import pytesseract
 
-# If the executable is not found, set the path explicitly
-pytesseract.pytesseract.tesseract_cmd = '/usr/bin/tesseract'  # Adjust if necessary
+pytesseract.pytesseract.tesseract_cmd = '/usr/bin/tesseract' 
+
 
-# Load the LayoutLMv3 model and processor
 processor = AutoProcessor.from_pretrained("microsoft/layoutlmv3-base", apply_ocr=True)
 model = AutoModelForTokenClassification.from_pretrained("capitaletech/language-levels-LayoutLMv3-v4")
 
@@ -37,23 +36,18 @@ def iob_to_label(label):
 def process_image(image):
     width, height = image.size
 
-    # Encode
     encoding = processor(image, truncation=True, return_offsets_mapping=True, return_tensors="pt")
     offset_mapping = encoding.pop('offset_mapping')
 
-    # Forward pass
     outputs = model(**encoding)
 
-    # Get predictions
     predictions = outputs.logits.argmax(-1).squeeze().tolist()
     token_boxes = encoding.bbox.squeeze().tolist()
 
-    # Only keep non-subword predictions
     is_subword = np.array(offset_mapping.squeeze().tolist())[:, 0] != 0
     true_predictions = [id2label[pred] for idx, pred in enumerate(predictions) if not is_subword[idx]]
     true_boxes = [unnormalize_box(box, width, height) for idx, box in enumerate(token_boxes) if not is_subword[idx]]
 
-    # Draw predictions over the image
     draw = ImageDraw.Draw(image)
     font = ImageFont.load_default()
     for prediction, box in zip(true_predictions, true_boxes):
@@ -63,7 +57,6 @@ def process_image(image):
 
     return image
 
-# Streamlit UI
 st.title("Language Levels Extraction using LayoutLMv3 Model")
 st.write("Use this application to predict language levels in CVs.")