larshiakzemil/glm-ocr-farsi

import torch
from PIL import Image
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "larshiakzemil/glm-ocr-farsi"
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.bfloat16 if device == "cuda" else torch.float32

processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    model_id, trust_remote_code=True, dtype=dtype, device_map=device
)
model.eval()

image = Image.open("page.jpg").convert("RGB")
messages = [{
    "role": "user",
    "content": [
        {"type": "image", "image": image},
        {"type": "text", "text": "Text Recognition:"},
    ],
}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt")
inputs = {k: v.to(device) if hasattr(v, "to") else v for k, v in inputs.items()}

with torch.inference_mode():
    out = model.generate(**inputs, max_new_tokens=512, do_sample=False)

decoded = processor.decode(out[0], skip_special_tokens=True)
print(decoded.split("Text Recognition:", 1)[-1].strip())