Update app_inference.py

app_interface.py

@@ -1,38 +1,53 @@
-from typing import List
-
-import pytesseract
 from PIL import Image
-
+import pytesseract
 import gradio as gr
+import os
+langs = []
+
+choices = os.popen('tesseract --list-langs').read().split('\n')[1:-1]
+
+blocks = gr.Blocks()
+
+
+# If you don't have tesseract executable in your PATH, include the following:
+# pytesseract.pytesseract.tesseract_cmd = r'<full_path_to_your_tesseract_executable>'
+# Example tesseract_cmd = r'C:\Program Files (x86)\Tesseract-OCR\tesseract'
+
+# Simple image to string
+# print(pytesseract.image_to_string(Image.open('eurotext.png')))
+
+# # French text image to string
+# print(pytesseract.image_to_string(Image.open('test-european.jpg'), lang='fra'))
+
+# # Get bounding box estimates
+# print(pytesseract.image_to_boxes(Image.open('test.png')))
+
+# # Get verbose data including boxes, confidences, line and page numbers
+# print(pytesseract.image_to_data(Image.open('test.png')))
+
+# # Get information about orientation and script detection
+# print(pytesseract.image_to_osd(Image.open('test.png'))
+
+
+def run(image, lang=None):
+    result = pytesseract.image_to_string(
+        image, lang=None if lang == [] else lang)
+    return result
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Hello pytesseract!")
+    with gr.Row():
+        with gr.Column():
+            image_in = gr.Image(type="pil")
+            lang = gr.Dropdown(choices)
+            btn = gr.Button("Run")
+        with gr.Column():
+            text_out = gr.TextArea()
+
+    examples = gr.Examples([["./eurotext.png", None]], fn=run, inputs=[
+                           image_in, lang], outputs=[text_out], cache_examples=False)
+    btn.click(fn=run, inputs=[image_in, lang], outputs=[text_out])
+
+demo.launch()
 
-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")