import gradio as gr import pytesseract from PIL import Image def tesseract_ocr(filepath, languages): image = Image.open(filepath) return pytesseract.image_to_string(image=image, lang=', '.join(languages) if languages else None) title = "Tesseract OCR" description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine." article = "

Tesseract documentation | Github Repo

" examples = [ ["examples/eurotext.png", ["eng"]], ["examples/tesseract_sample.png", ["jpn", "eng"]], ["examples/chi.jpg", ["HanS", "HanT"]], ] with gr.Blocks(title=title) as demo: gr.Markdown(f'

{title}

') gr.Markdown(description) with gr.Row(): with gr.Column(): image = gr.Image(type="filepath", label="Input") language_choices = pytesseract.get_languages() with gr.Accordion("Languages", open=False): languages = gr.CheckboxGroup(language_choices, type="value", value=["eng"], label='language') with gr.Row(): btn_clear = gr.ClearButton([image, languages]) btn_submit = gr.Button(value="Submit", variant="primary") with gr.Column(): text = gr.Textbox(label="Output") btn_submit.click(tesseract_ocr, inputs=[image, languages], outputs=text) btn_clear.add(text) gr.Examples( examples=examples, inputs=[image, languages], ) gr.Markdown(article) if __name__ == '__main__': demo.launch()