ekizcemelih/TAMGA-tr-image-captioning-blip

---

language: tr tags: - image-captioning - blip - generated_from_trainer library_name: transformers

Türkçe Görsel Açıklama Modeli (Turkish Image Captioning)

Bu model, görselleri analiz ederek Türkçe açıklamalar üretmek üzere fine-tune edilmiştir.

Kullanım (Usage)

from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image
import requests

# Modeli yükle
processor = BlipProcessor.from_pretrained("ekizcemelih/TAMGA-tr-image-captioning-blip")
model = BlipForConditionalGeneration.from_pretrained("ekizcemelih/TAMGA-tr-image-captioning-blip")

# Görseli yükle
img_url = '[https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg](https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg)' 
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

# Model girdisini hazırla
inputs = processor(raw_image, return_tensors="pt")

# Çıktı üret
out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))