Spaces:
Sleeping
Sleeping
import gradio as gr | |
from transformers import TrOCRProcessor, VisionEncoderDecoderModel | |
from PIL import Image | |
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten") | |
model = VisionEncoderDecoderModel.from_pretrained("quocanh944/tr-ocr") | |
# load image examples from the IAM database | |
urls = ['./images/a01-000u-00.png', | |
'./images/a01-000x-04.png', | |
'./images/a01-003-10.png'] | |
for idx, url in enumerate(urls): | |
image = Image.open(url) | |
image.save(f"image_{idx}.png") | |
def process_image(image): | |
# prepare image | |
pixel_values = processor(image, return_tensors="pt").pixel_values | |
# generate (no beam search) | |
generated_ids = model.generate(pixel_values) | |
# decode | |
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] | |
return generated_text | |
title = "Interactive demo: 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 on IAM, a dataset of annotated handwritten images. To use it, simply upload an image or use the example image below and click 'submit'. Results will show up in a few seconds." | |
article = "TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models | Github Repo" | |
examples =[["image_0.png"], ["image_1.png"], ["image_2.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() |