|
Download ABOUT.md from kesha-humonen/runic-reader: direct link, hf CLI and curl.
- Browser
- Download file 1.94 kB
-
https://huggingface.co/kesha-humonen/runic-reader/resolve/main/ABOUT.md
- Command line
-
hf download hf://kesha-humonen/runic-reader/ABOUT.md
-
curl -L -o ABOUT.md https://huggingface.co/kesha-humonen/runic-reader/resolve/main/ABOUT.md
1.94 kB
How it works
- Localization. Qwen3.5-4B without fine-tuning returns a bounding box of the inscription; the photograph is cropped with a 20% margin and rescaled to about 0.64 megapixels.
- Recognition. A LoRA adapter trained on real and procedurally generated rune images transcribes the crop in the Rundata convention. A second recognizer, trained on whole photographs, reads the same image; words on which the two disagree are flagged for checking.
- Identification. The (corrected) transliteration is searched against 10,125 records from Rundata and RuneS (character 3-grams, TF-IDF, cosine). The confidence is the score gap between the best record and the best record of a different inscription, calibrated on held-out test photographs.
- Translation. For inscriptions that are not found, a LoRA translator produces a draft translation into English or Swedish.
How well it works (550 held-out test photographs)
| words corrected by the user | 0 | 1 | 2 | 3 | 5 | 10 |
|---|---|---|---|---|---|---|
| correct inscription ranked first, % (flagged words first) | 30.9 | 44.4 | 55.5 | 64.0 | 80.9 | 92.2 |
| character error rate of the text, % | 71.7 | 66.8 | 62.9 | 58.7 | 49.3 | 28.9 |
The simulated user fixes one word error at a time, first among the flagged words; “Simulated expert” in the first tab does exactly this. Among the 10% of photographs with the largest match margin, identification is correct 72.7% of the time without any correction.
Limitations
Recognition from photographs remains hard: most raw readings contain several wrong words, and identification only works for inscriptions already in the corpus. Translations of noisy readings are drafts, not scholarly interpretations.
Data and licences
Corpus texts: Samnordisk runtextdatabas (Rundata) and RuneS-DB. Photographs: RuneS-DB records with the photographer and licence shown next to each image.