Upload folder using huggingface_hub
Browse files
README.md
CHANGED
@@ -1,5 +1,14 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
4 |
|
5 |
# ch_RepSVTR_rec
|
@@ -12,21 +21,17 @@ RepSVTR is a mobile-side text recognition model based on SVTRv2. It won the firs
|
|
12 |
<tr>
|
13 |
<th>Model</th>
|
14 |
<th>Recognition Avg Accuracy(%)</th>
|
15 |
-
<th>GPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
|
16 |
-
<th>CPU Inference Time (ms)<br/>[Normal Mode / High-Performance Mode]</th>
|
17 |
<th>Model Storage Size (M)</th>
|
18 |
</tr>
|
19 |
<tr>
|
20 |
<td>ch_RepSVTR_rec</td>
|
21 |
<td>65.07</td>
|
22 |
-
<td>5.93 / 1.62</td>
|
23 |
-
<td>20.73 / 7.32</td>
|
24 |
<td>22.1 M</td>
|
25 |
</tr>
|
26 |
</table>
|
27 |
|
28 |
|
29 |
-
**Note**: If any character (including punctuation) in a line
|
30 |
|
31 |
## Quick Start
|
32 |
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
library_name: PaddleOCR
|
4 |
+
language:
|
5 |
+
- en
|
6 |
+
- zh
|
7 |
+
pipeline_tag: image-to-text
|
8 |
+
tags:
|
9 |
+
- OCR
|
10 |
+
- PaddlePaddle
|
11 |
+
- PaddleOCR
|
12 |
---
|
13 |
|
14 |
# ch_RepSVTR_rec
|
|
|
21 |
<tr>
|
22 |
<th>Model</th>
|
23 |
<th>Recognition Avg Accuracy(%)</th>
|
|
|
|
|
24 |
<th>Model Storage Size (M)</th>
|
25 |
</tr>
|
26 |
<tr>
|
27 |
<td>ch_RepSVTR_rec</td>
|
28 |
<td>65.07</td>
|
|
|
|
|
29 |
<td>22.1 M</td>
|
30 |
</tr>
|
31 |
</table>
|
32 |
|
33 |
|
34 |
+
**Note**: If any character (including punctuation) in a line was incorrect, the entire line was marked as wrong. This ensures higher accuracy in practical applications.
|
35 |
|
36 |
## Quick Start
|
37 |
|