laicsiifes
/

swin-gportuguese-2

vision-encoder-decoder

image-text-to-text

Inference Endpoints

Model card Files Files and versions Community

gabrielmotablima commited on Sep 2

Commit

c2b972b

•

1 Parent(s): 4ca27c2

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -44,7 +44,7 @@ from transformers import AutoTokenizer, ViTImageProcessor, VisionEncoderDecoderM
 # load a fine-tuned image captioning model and corresponding tokenizer and image processor
 model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
-tokenizer = GPT2TokenizerFast.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
 image_processor = ViTImageProcessor.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
 # perform inference on an image

 # load a fine-tuned image captioning model and corresponding tokenizer and image processor
 model = VisionEncoderDecoderModel.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
+tokenizer = AutoTokenizer.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
 image_processor = ViTImageProcessor.from_pretrained("laicsiifes/swin-gpt2-flickr30k-pt-br")
 # perform inference on an image