File size: 1,525 Bytes
c30f358 b6d1465 4d7290f b6d1465 c30f358 |
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 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
import os
from transformers import AutoModel, AutoTokenizer
from PIL import Image
import torch
class OCRModel:
_instance = None
def __new__(cls):
if cls._instance is None:
cls._instance = super(OCRModel, cls).__new__(cls)
cls._instance.initialize()
return cls._instance
def initialize(self):
# تحميل النموذج مرة واحدة وتخزينه محلياً
model_path = os.getenv('MODEL_PATH', 'RufusRubin777/GOT-OCR2_0_CPU')
self.tokenizer = AutoTokenizer.from_pretrained(
model_path,
trust_remote_code=True,
local_files_only=False # سيتم تحميل الملفات إذا لم تكن موجودة
)
self.model = AutoModel.from_pretrained(
model_path,
trust_remote_code=True,
low_cpu_mem_usage=True,
device_map='cpu', # سيختار أفضل جهاز متاح
use_safetensors=True,
pad_token_id=self.tokenizer.eos_token_id
)
self.model = self.model.eval()
def process_image(self, image_stream):
try:
# فتح الصورة من الذاكرة
image = Image.open(image_stream)
with torch.no_grad():
result = self.model.chat(self.tokenizer, image, ocr_type='format')
return result
except Exception as e:
return f"Error processing image: {str(e)}" |