Update ocr_engine.py

ocr_engine.py

@@ -1,24 +1,21 @@
-from transformers import DonutProcessor, VisionEncoderDecoderModel
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
 from PIL import Image
 import re
 
-# Load OCR processor and model (pretrained on receipts, good for 7-segment)
-processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
-model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+# Load smaller/faster model
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-small-printed")
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-small-printed")
 
 def extract_weight(image: Image.Image) -> str:
     image = image.convert("RGB")
-    pixel_values = processor(image, return_tensors="pt").pixel_values
+    pixel_values = processor(images=image, return_tensors="pt").pixel_values
+    generated_ids = model.generate(pixel_values, max_length=32)
+    full_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
 
-    outputs = model.generate(pixel_values, max_length=512)
-    decoded = processor.batch_decode(outputs, skip_special_tokens=True)[0]
-
-    # Extract weight number
-    cleaned = decoded.lower().replace(" ", "")
+    cleaned = full_text.lower().replace(" ", "")
     match = re.search(r"(\d+(\.\d+)?)", cleaned)
     weight = match.group(1) if match else None
 
-    # Smart unit detection
     if any(u in cleaned for u in ["kg", "kgs", "kilogram", "kilo"]):
         unit = "kg"
     elif any(u in cleaned for u in ["g", "gram", "grams"]):
@@ -26,4 +23,4 @@ def extract_weight(image: Image.Image) -> str:
     else:
         unit = "kg" if weight and float(weight) >= 5 else "grams"
 
-    return f"{weight} {unit}" if weight else "No valid weight detected"
+    return f"{weight} {unit}" if weight else ""