Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,10 +1,22 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: docker
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: OCR Bench Viewer
|
| 3 |
+
emoji: "🔍"
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: gray
|
| 6 |
sdk: docker
|
| 7 |
+
app_port: 7860
|
| 8 |
+
tags:
|
| 9 |
+
- ocr
|
| 10 |
+
- leaderboard
|
| 11 |
+
- vlm-judge
|
| 12 |
---
|
| 13 |
|
| 14 |
+
# OCR Bench Viewer
|
| 15 |
+
|
| 16 |
+
Browse OCR model evaluation results with per-dataset leaderboards.
|
| 17 |
+
|
| 18 |
+
Rankings change by document type — manuscript cards, printed books, historical texts all produce different winners.
|
| 19 |
+
|
| 20 |
+
**Currently showing:** BPL card catalog results (4 models, VLM-as-judge).
|
| 21 |
+
|
| 22 |
+
Keyboard shortcuts: arrow keys to navigate, `a`/`b`/`t` to vote, `r` to reveal judge verdict.
|