Spaces:
Sleeping
Sleeping
Update app.py
Browse filesImprove wording
app.py
CHANGED
|
@@ -83,14 +83,16 @@ with gr.Blocks(title="OCR QA Demo") as demo:
|
|
| 83 |
|
| 84 |
gr.Markdown(
|
| 85 |
"""
|
| 86 |
-
|
| 87 |
-
|
| 88 |
-
|
| 89 |
-
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
|
| 93 |
-
|
|
|
|
|
|
|
| 94 |
)
|
| 95 |
|
| 96 |
with gr.Row():
|
|
|
|
| 83 |
|
| 84 |
gr.Markdown(
|
| 85 |
"""
|
| 86 |
+
# π OCR Quality Assessment Demo
|
| 87 |
+
|
| 88 |
+
This demo showcases the **OCR Quality Assessment (OCRQA)** pipeline developed as part of the [Impresso Project](https://impresso-project.ch). The pipeline evaluates the quality of text extracted via **Optical Character Recognition (OCR)** by estimating the proportion of recognizable words.
|
| 89 |
+
|
| 90 |
+
It returns:
|
| 91 |
+
- a **quality score** between **0.0 (poor)** and **1.0 (excellent)**, and
|
| 92 |
+
- a list of **potential OCR errors** (unrecognized tokens).
|
| 93 |
+
|
| 94 |
+
You can try the example below (a German text containing typical OCR errors), or paste your own OCR-processed text to assess its quality.
|
| 95 |
+
"""
|
| 96 |
)
|
| 97 |
|
| 98 |
with gr.Row():
|