Image-to-Text
Transformers
PyTorch
JAX
Portuguese
vision-encoder-decoder
image-text-to-text
image-captioning
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM
tokenizer = AutoTokenizer.from_pretrained("adalbertojunior/image_captioning_portuguese")
model = AutoModelForMultimodalLM.from_pretrained("adalbertojunior/image_captioning_portuguese", device_map="auto")Quick Links
Image Captioning in Portuguese trained with ViT and GPT2
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC)
- Downloads last month
- 22
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="adalbertojunior/image_captioning_portuguese")