.

README.md

@@ -1,11 +1,11 @@
 ---
 title: Tesseract OCR
-emoji: 🔥
-colorFrom: red
-colorTo: blue
+emoji: 🐢
+colorFrom: blue
+colorTo: purple
 sdk: gradio
-sdk_version: 4.15.0
-app_file: app.py
+sdk_version: 3.40.1
+app_file: app_blocks.py
 pinned: false
 ---
 

app_blocks.py

@@ -0,0 +1,48 @@
+from typing import List
+
+import pytesseract
+from PIL import Image
+
+import gradio as gr
+
+def tesseract_ocr(filepath: str, languages: List[str]=None):
+    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 = "<p style='text-align: center'><a href='https://tesseract-ocr.github.io/' target='_blank'>Tesseract documentation</a> | <a href='https://github.com/tesseract-ocr/tesseract' target='_blank'>Github Repo</a></p>"
+examples = [
+    ["examples/weird_unicode_math_symbols.png", []],
+    ["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'<h1 style="text-align: center; margin-bottom: 1rem;">{title}</h1>')
+    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, api_name="tesseract-ocr")
+    btn_clear.add(text)
+
+    gr.Examples(
+        examples=examples,
+        inputs=[image, languages],
+    )
+
+    gr.Markdown(article)
+
+if __name__ == '__main__':
+    demo.launch()

app_interface.py

@@ -0,0 +1,38 @@
+from typing import List
+
+import pytesseract
+from PIL import Image
+
+import gradio as gr
+
+def tesseract_ocr(filepath: str, languages: List[str]):
+    image = Image.open(filepath)
+    return pytesseract.image_to_string(image=image, lang=', '.join(languages))
+
+title = "Tesseract OCR"
+description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine."
+article = "<p style='text-align: center'><a href='https://tesseract-ocr.github.io/' target='_blank'>Tesseract documentation</a> | <a href='https://github.com/tesseract-ocr/tesseract' target='_blank'>Github Repo</a></p>"
+examples = [
+        ['examples/eurotext.png', ['eng']], 
+        ['examples/tesseract_sample.png', ['jpn', 'eng']], 
+        ['examples/chi.jpg', ['HanS', 'HanT']]
+    ]
+
+language_choices = pytesseract.get_languages()
+
+demo = gr.Interface(
+    fn=tesseract_ocr, 
+    inputs=[
+        gr.Image(type="filepath", label="Input"), 
+        gr.CheckboxGroup(language_choices, type="value", value=['eng'], label='language')
+        ],
+    outputs='text',
+    title=title,
+    description=description,
+    article=article,
+    examples=examples,
+)
+
+if __name__ == '__main__':
+    demo.launch()
+    print("Finished running")

packages.txt

@@ -0,0 +1 @@
+tesseract-ocr-all

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+pytesseract