Spaces:
Sleeping
Sleeping
| # impoprt packages | |
| import torch | |
| import requests | |
| from PIL import Image | |
| from transformers import BlipProcessor, BlipForConditionalGeneration, AutoTokenizer, pipeline | |
| import sentencepiece | |
| import gradio as gr | |
| # Image captioning model | |
| processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base") | |
| model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base") | |
| # Translate en to ar | |
| model_translater = pipeline("translation", model="Helsinki-NLP/opus-mt-tc-big-en-ar") | |
| # conditional image captioning (with prefix-) | |
| def image_captioning(image, prefix="a "): | |
| """ Return text (As str) to describe an image """ | |
| # Process the image | |
| inputs = processor(image, prefix, return_tensors="pt") | |
| # Generate text to describe the image | |
| output = model.generate(**inputs) | |
| # Decode the output | |
| output = processor.decode(output[0], skip_special_tokens=True, max_length=80) | |
| return output | |
| def translate_text(text, to="ar"): | |
| """ Return translated text """ | |
| translated_text = model_translater(str(text)) | |
| return translated_text[0]['translation_text'] | |
| def image_captioning_ar(image, prefix = "a "): | |
| if image: | |
| text = image_captioning(image, prefix=prefix) | |
| return text, translate_text(text) | |
| return null | |
| input_image = gr.inputs.Image(type="pil", label = 'Upload your image') | |
| imageCaptioning_interface = gr.Interface( | |
| fn = image_captioning_ar, | |
| inputs=input_image, | |
| outputs=[gr.outputs.Textbox(label="Caption (en)"), gr.outputs.Textbox(label="Caption (ar)")], | |
| title = 'Image captioning', | |
| ) | |
| imageCaptioning_interface.launch() |