OttomanNLP/Azra-1-Mini-0.8b

import os
import torch
from PIL import Image
from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
from qwen_vl_utils import process_vision_info

# Device & dtype settings
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if device == "cuda" else torch.float32

model_id = "OttomanNLP/Azra-1-Mini-0.8b"

print("[INFO] Loading model and processor...")
processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = Qwen3_5ForConditionalGeneration.from_pretrained(
    model_id,
    torch_dtype=dtype,
    device_map="auto" if device == "cuda" else None,
    trust_remote_code=True
)
model.eval()
print("[INFO] Model loaded successfully!")

def extract_text(image_path: str, prompt: str = "Görseldeki Osmanlıca metni transkribe et:") -> str:
    """Extract Ottoman text from a line image"""
    if not os.path.exists(image_path):
        return f"File not found: {image_path}"
        
    image = Image.open(image_path).convert("RGB")
    
    # Adjust dimensions to multiples of 64
    w, h = image.size
    new_w = ((w + 63) // 64) * 64
    new_h = ((h + 63) // 64) * 64
    if (new_w, new_h) != (w, h):
        image = image.resize((new_w, new_h), Image.Resampling.LANCZOS)
    
    messages = [{
        "role": "user",
        "content": [
            {"type": "image", "image": image},
            {"type": "text", "text": prompt}
        ]
    }]
    
    text_input = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )
    image_inputs, _ = process_vision_info(messages)
    
    inputs = processor(
        text=[text_input],
        images=image_inputs,
        padding=True,
        return_tensors="pt"
    ).to(device)
    
    with torch.inference_mode():
        generated_ids = model.generate(
            **inputs,
            max_new_tokens=512,
            do_sample=False,
            repetition_penalty=1.2,
            no_repeat_ngram_size=3,
            pad_token_id=processor.tokenizer.pad_token_id,
            eos_token_id=processor.tokenizer.eos_token_id,
        )
    
    input_len = inputs.input_ids.shape[1]
    output_text = processor.batch_decode(
        generated_ids[:, input_len:],
        skip_special_tokens=True,
        clean_up_tokenization_spaces=False
    )[0]
    
    return output_text.strip()

if __name__ == "__main__":
    image_path = "sample_line.png"  # Path to line-level image
    text = extract_text(image_path)
    print("📝 Transcribed Text:\n", text)

@article{usta2026cross,
  title={Cross-Lingual Transfer Learning and Autonomous Data Bootstrapping for VLM-Based Ottoman Turkish Handwritten Text Recognition},
  author={Usta, G{\"o}khan and Alpo{\u{g}}lu, O{\u{g}}uz and G{\"u}nayd{\i}n, Fatih},
  journal={Research Square (Preprint)},
  year={2026},
  doi={10.21203/rs.3.rs-10418926/v1},
  note={Under Review at International Journal on Document Analysis and Recognition (IJDAR)}
}