simon-clmtd commited on
Commit
70a1f99
Β·
verified Β·
1 Parent(s): 6acad0f

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +1 -3
app.py CHANGED
@@ -92,7 +92,7 @@ with gr.Blocks(title="OCR QA Demo") as demo:
92
  # πŸ” OCR Quality Assessment Demo
93
 
94
  This demo showcases the **OCR Quality Assessment (OCRQA)** of the [Impresso Project](https://impresso-project.ch).
95
- The pipeline evaluates the quality of text extracted via **Optical Character Recognition (OCR)** by estimating the proportion of recognizable words.
96
 
97
  It returns:
98
  - a **quality score** between **0.0 (poor)** and **1.0 (excellent)**, and
@@ -131,8 +131,6 @@ with gr.Blocks(title="OCR QA Demo") as demo:
131
  with gr.Accordion("πŸ“ About the OCR QA Method", open=False, visible=False) as info_accordion:
132
  gr.Markdown(
133
  """
134
- ### πŸ“ About the OCR QA Method
135
-
136
  This pipeline estimates OCR quality by analyzing the proportion of **unique words** in a text that match curated wordlists for a given language.
137
 
138
  #### How it works:
 
92
  # πŸ” OCR Quality Assessment Demo
93
 
94
  This demo showcases the **OCR Quality Assessment (OCRQA)** of the [Impresso Project](https://impresso-project.ch).
95
+ The pipeline evaluates the quality of text extracted via Optical Character Recognition (OCR) by estimating the proportion of (un)known words with respect to a large clean text corpus.
96
 
97
  It returns:
98
  - a **quality score** between **0.0 (poor)** and **1.0 (excellent)**, and
 
131
  with gr.Accordion("πŸ“ About the OCR QA Method", open=False, visible=False) as info_accordion:
132
  gr.Markdown(
133
  """
 
 
134
  This pipeline estimates OCR quality by analyzing the proportion of **unique words** in a text that match curated wordlists for a given language.
135
 
136
  #### How it works: