Spaces:
Running
Running
File size: 1,170 Bytes
dd1ae7e 65ef5f8 d22d28e 65ef5f8 33c8720 dd1ae7e 65ef5f8 513f893 dd1ae7e 65ef5f8 dd1ae7e 513f893 33c8720 a4b646d 5217dbe fb27fac 33c8720 a4b646d fb27fac a4b646d fb27fac 5217dbe fb27fac 5217dbe |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 |
from transformers import DonutProcessor, 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")
def extract_weight(image: Image.Image) -> str:
image = image.convert("RGB")
pixel_values = processor(image, return_tensors="pt").pixel_values
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(" ", "")
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"]):
unit = "grams"
else:
unit = "kg" if weight and float(weight) >= 5 else "grams"
return f"{weight} {unit}" if weight else "No valid weight detected"
|