secc

app_blocks.py

@@ -3,7 +3,6 @@ import pytesseract
 from PIL import Image
 import gradio as gr
 
-# OCR function
 def tesseract_ocr(filepath: str, languages: List[str] = None):
     if not languages:
         languages = ['eng']
@@ -11,17 +10,15 @@ def tesseract_ocr(filepath: str, languages: List[str] = None):
     lang_param = '+'.join(languages)
     return pytesseract.image_to_string(image=image, lang=lang_param)
 
-# Metadata
 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>"
 
-# Local examples
 examples = [
     ["examples/weird_unicode_math_symbols.png", []],
     ["examples/eurotext.png", ["eng"]],
     ["examples/tesseract_sample.png", ["jpn", "eng"]],
-    ["examples/chi.jpg", ["HanS", "HanT"]],
+    ["examples/chi.jpg", ["chi_sim", "chi_tra"]],
 ]
 
 with gr.Blocks(title=title) as demo:
@@ -31,7 +28,7 @@ with gr.Blocks(title=title) as demo:
     with gr.Row():
         with gr.Column():
             image = gr.Image(type="filepath", label="Input")
-            language_choices = pytesseract.get_languages()
+            language_choices = pytesseract.get_languages(config='')  # <- safer
             with gr.Accordion("Languages", open=False):
                 languages = gr.CheckboxGroup(language_choices, value=["eng"], label="Language(s)")
             with gr.Row():
@@ -44,7 +41,6 @@ with gr.Blocks(title=title) as demo:
     btn_submit.click(tesseract_ocr, inputs=[image, languages], outputs=text)
     btn_clear.add(text)
 
-    # ✅ Function bound directly here
     gr.Examples(
         examples=examples,
         inputs=[image, languages],
@@ -54,6 +50,5 @@ with gr.Blocks(title=title) as demo:
 
     gr.Markdown(article)
 
-# ✅ Required for Spaces
 if __name__ == '__main__':
     demo.queue().launch()