app.py

import pandas as pd
import PIL
from PIL import Image
from PIL import ImageDraw
import gradio as gr
import torch
import easyocr

processor = AutoProcessor.from_pretrained("Sharka/CIVQA_LayoutLMv2_EasyOCR")
model = AutoModelForDocumentQuestionAnswering.from_pretrained("Sharka/CIVQA_LayoutLMv2_EasyOCR")

def draw_boxes(image, bounds, color='red', width=2):
    draw = ImageDraw.Draw(image)
    for bound in bounds:
        p0, p1, p2, p3 = bound[0]
        draw.line([*p0, *p1, *p2, *p3, *p0], fill=color, width=width)
    return image

def inference(img, lang):
    reader = easyocr.Reader(lang)
    bounds = reader.readtext(img.name)
    im = PIL.Image.open(img.name)
    draw_boxes(im, bounds)
    im.save('result.jpg')
    return ['result.jpg', pd.DataFrame(bounds).iloc[: , 1:]]

gr.Interface(
    inference,
    [gr.inputs.Image(type='file', label='Input'),gr.inputs.CheckboxGroup(choices, type="value", default=['en', 'vi'], label='language')],
    [gr.outputs.Image(type='file', label='Output'), gr.outputs.Dataframe(headers=['text', 'confidence'])],
    enable_queue=True
    ).launch(debug=True)