|
import gradio as gr |
|
from transformers import TrOCRProcessor, VisionEncoderDecoderModel |
|
import requests |
|
from PIL import Image |
|
|
|
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-str") |
|
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-str") |
|
|
|
|
|
urls = ['https://i.postimg.cc/ZKwLg2Gw/367-14.png'] |
|
for idx, url in enumerate(urls): |
|
image = Image.open(requests.get(url, stream=True).raw) |
|
image.save(f"image_{idx}.png") |
|
|
|
def process_image(image): |
|
|
|
pixel_values = processor(image, return_tensors="pt").pixel_values |
|
|
|
|
|
generated_ids = model.generate(pixel_values) |
|
|
|
|
|
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] |
|
|
|
return generated_text |
|
|
|
title = "Interactive demo: Scene Text Recognition with TrOCR" |
|
description = "Demo for Microsoft's TrOCR, an encoder-decoder model consisting of an image Transformer encoder and a text Transformer decoder for state-of-the-art optical character recognition (OCR) on single-text line images. This particular model is fine-tuned for scene text recognition. To use it, simply upload a (single-text line) image or use one of the example images below and click 'submit'. Results will show up in a few seconds." |
|
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2109.10282'>TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models</a> | <a href='https://github.com/microsoft/unilm/tree/master/trocr'>Github Repo</a></p>" |
|
examples =[["image_0.png"]] |
|
|
|
|
|
|
|
iface = gr.Interface(fn=process_image, |
|
inputs=gr.inputs.Image(type="pil"), |
|
outputs=gr.outputs.Textbox(), |
|
title=title, |
|
description=description, |
|
article=article, |
|
examples=examples) |
|
iface.launch(debug=True) |
