| from transformers import pipeline | |
| image_to_text = pipeline("image-to-text", model="nlpconnect/vit-gpt2-image-captioning") | |
| image_to_text("https://ankur3107.github.io/assets/images/image-captioning-example.png") | |
| # [{'generated_text': 'a soccer game with a player jumping to catch the ball '}] | |