File size: 1,593 Bytes
a5d977a 235ef43 a5d977a 235ef43 a5d977a 235ef43 8960167 a5d977a bba69da a5d977a bba69da 8960167 a5d977a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
# 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() |