Spaces:
Running
Running
The Recovered Page — Tufte reader for Surya OCR 2 on Europeana newspapers
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +107 -0
- README.md +19 -3
- data.json +0 -0
- img/000.jpg +3 -0
- img/001.jpg +3 -0
- img/002.jpg +3 -0
- img/003.jpg +3 -0
- img/004.jpg +3 -0
- img/005.jpg +3 -0
- img/006.jpg +3 -0
- img/007.jpg +3 -0
- img/008.jpg +3 -0
- img/009.jpg +3 -0
- img/010.jpg +3 -0
- img/011.jpg +3 -0
- img/012.jpg +3 -0
- img/013.jpg +3 -0
- img/014.jpg +3 -0
- img/015.jpg +3 -0
- img/016.jpg +3 -0
- img/017.jpg +3 -0
- img/018.jpg +3 -0
- img/019.jpg +3 -0
- img/020.jpg +3 -0
- img/021.jpg +3 -0
- img/022.jpg +3 -0
- img/023.jpg +3 -0
- img/024.jpg +3 -0
- img/025.jpg +3 -0
- img/026.jpg +3 -0
- img/027.jpg +3 -0
- img/028.jpg +3 -0
- img/029.jpg +3 -0
- img/030.jpg +3 -0
- img/031.jpg +3 -0
- img/032.jpg +3 -0
- img/033.jpg +3 -0
- img/034.jpg +3 -0
- img/035.jpg +3 -0
- img/036.jpg +3 -0
- img/037.jpg +3 -0
- img/038.jpg +3 -0
- img/039.jpg +3 -0
- img/040.jpg +3 -0
- img/041.jpg +3 -0
- img/042.jpg +3 -0
- img/043.jpg +3 -0
- img/044.jpg +3 -0
- img/045.jpg +3 -0
- img/046.jpg +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,110 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
img/000.jpg filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
img/001.jpg filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
img/002.jpg filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
img/003.jpg filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
img/004.jpg filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
img/005.jpg filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
img/006.jpg filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
img/007.jpg filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
img/008.jpg filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
img/009.jpg filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
img/010.jpg filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
img/011.jpg filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
img/012.jpg filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
img/013.jpg filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
img/014.jpg filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
img/015.jpg filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
img/016.jpg filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
img/017.jpg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
img/018.jpg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
img/019.jpg filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
img/020.jpg filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
img/021.jpg filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
img/022.jpg filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
img/023.jpg filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
img/024.jpg filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
img/025.jpg filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
img/026.jpg filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
img/027.jpg filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
img/028.jpg filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
img/029.jpg filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
img/030.jpg filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
img/031.jpg filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
img/032.jpg filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
img/033.jpg filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
img/034.jpg filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
img/035.jpg filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
img/036.jpg filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
img/037.jpg filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
img/038.jpg filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
img/039.jpg filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
img/040.jpg filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
img/041.jpg filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
img/042.jpg filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
img/043.jpg filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
img/044.jpg filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
img/045.jpg filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
img/046.jpg filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
img/047.jpg filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
img/048.jpg filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
img/049.jpg filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
img/050.jpg filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
img/051.jpg filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
img/052.jpg filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
img/053.jpg filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
img/054.jpg filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
img/055.jpg filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
img/056.jpg filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
img/057.jpg filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
img/058.jpg filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
img/059.jpg filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
img/060.jpg filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
img/061.jpg filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
img/062.jpg filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
img/063.jpg filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
img/064.jpg filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
img/065.jpg filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
img/066.jpg filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
img/067.jpg filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
img/068.jpg filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
img/069.jpg filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
img/070.jpg filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
img/071.jpg filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
img/072.jpg filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
img/073.jpg filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
img/074.jpg filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
img/075.jpg filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
img/076.jpg filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
img/077.jpg filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
img/078.jpg filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
img/079.jpg filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
img/080.jpg filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
img/081.jpg filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
img/082.jpg filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
img/083.jpg filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
img/084.jpg filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
img/085.jpg filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
img/086.jpg filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
img/087.jpg filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
img/088.jpg filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
img/089.jpg filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
img/090.jpg filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
img/091.jpg filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
img/092.jpg filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
img/093.jpg filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
img/094.jpg filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
img/095.jpg filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
img/096.jpg filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
img/097.jpg filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
img/098.jpg filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
img/099.jpg filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
img/100.jpg filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
img/101.jpg filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
img/102.jpg filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
img/103.jpg filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
img/104.jpg filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
img/105.jpg filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
img/106.jpg filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,10 +1,26 @@
|
|
| 1 |
---
|
| 2 |
title: The Recovered Page
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
colorTo: red
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: The Recovered Page
|
| 3 |
+
emoji: 📰
|
| 4 |
+
colorFrom: gray
|
| 5 |
colorTo: red
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
short_description: Surya OCR 2 (650M) reads historic European newspapers
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# The Recovered Page
|
| 13 |
+
|
| 14 |
+
A minimal, Tufte-inspired viewer for **Surya OCR 2** (650M) transcribing historic
|
| 15 |
+
European newspaper scans — across **7 languages** and **2 scripts** (Latin + Cyrillic).
|
| 16 |
+
|
| 17 |
+
Each page shows the original scan beside the model's reading-order transcription. Toggle
|
| 18 |
+
to the **original Europeana OCR** to compare against decades-old text, or reveal the
|
| 19 |
+
**layout blocks** the model recovered (`surya_blocks` bounding boxes + reading-order path).
|
| 20 |
+
|
| 21 |
+
- **Pages**: sampled from [Europeana Newspapers](https://huggingface.co/datasets/biglam/europeana_newspapers) via IIIF (SBB Berlin · NLE Estonia · NLF Finland · NLP Poland · UB Belgrade)
|
| 22 |
+
- **Transcriptions**: [`davanstrien/europeana-surya-ocr-demo`](https://huggingface.co/datasets/davanstrien/europeana-surya-ocr-demo)
|
| 23 |
+
- **Recipe**: [`uv-scripts/ocr`](https://huggingface.co/datasets/uv-scripts/ocr) (`surya-ocr.py`)
|
| 24 |
+
|
| 25 |
+
OCR is imperfect — this is a first pass, not ground truth. ~2% of pages produced no text
|
| 26 |
+
(dense scans where full-page generation looped and the fallback returned empty).
|
data.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
img/000.jpg
ADDED
|
Git LFS Details
|
img/001.jpg
ADDED
|
Git LFS Details
|
img/002.jpg
ADDED
|
Git LFS Details
|
img/003.jpg
ADDED
|
Git LFS Details
|
img/004.jpg
ADDED
|
Git LFS Details
|
img/005.jpg
ADDED
|
Git LFS Details
|
img/006.jpg
ADDED
|
Git LFS Details
|
img/007.jpg
ADDED
|
Git LFS Details
|
img/008.jpg
ADDED
|
Git LFS Details
|
img/009.jpg
ADDED
|
Git LFS Details
|
img/010.jpg
ADDED
|
Git LFS Details
|
img/011.jpg
ADDED
|
Git LFS Details
|
img/012.jpg
ADDED
|
Git LFS Details
|
img/013.jpg
ADDED
|
Git LFS Details
|
img/014.jpg
ADDED
|
Git LFS Details
|
img/015.jpg
ADDED
|
Git LFS Details
|
img/016.jpg
ADDED
|
Git LFS Details
|
img/017.jpg
ADDED
|
Git LFS Details
|
img/018.jpg
ADDED
|
Git LFS Details
|
img/019.jpg
ADDED
|
Git LFS Details
|
img/020.jpg
ADDED
|
Git LFS Details
|
img/021.jpg
ADDED
|
Git LFS Details
|
img/022.jpg
ADDED
|
Git LFS Details
|
img/023.jpg
ADDED
|
Git LFS Details
|
img/024.jpg
ADDED
|
Git LFS Details
|
img/025.jpg
ADDED
|
Git LFS Details
|
img/026.jpg
ADDED
|
Git LFS Details
|
img/027.jpg
ADDED
|
Git LFS Details
|
img/028.jpg
ADDED
|
Git LFS Details
|
img/029.jpg
ADDED
|
Git LFS Details
|
img/030.jpg
ADDED
|
Git LFS Details
|
img/031.jpg
ADDED
|
Git LFS Details
|
img/032.jpg
ADDED
|
Git LFS Details
|
img/033.jpg
ADDED
|
Git LFS Details
|
img/034.jpg
ADDED
|
Git LFS Details
|
img/035.jpg
ADDED
|
Git LFS Details
|
img/036.jpg
ADDED
|
Git LFS Details
|
img/037.jpg
ADDED
|
Git LFS Details
|
img/038.jpg
ADDED
|
Git LFS Details
|
img/039.jpg
ADDED
|
Git LFS Details
|
img/040.jpg
ADDED
|
Git LFS Details
|
img/041.jpg
ADDED
|
Git LFS Details
|
img/042.jpg
ADDED
|
Git LFS Details
|
img/043.jpg
ADDED
|
Git LFS Details
|
img/044.jpg
ADDED
|
Git LFS Details
|
img/045.jpg
ADDED
|
Git LFS Details
|
img/046.jpg
ADDED
|
Git LFS Details
|