Upload README.md with huggingface_hub

README.md

@@ -1,9 +1,54 @@
 ---
 license: cc-by-nc-sa-4.0
+pipeline_tag: object-detection
+language:
+  - gmy
+tags:
+  - linear-a
+  - linear-b
+  - aegean-scripts
+  - epigraphy
+  - ancient-languages
+  - object-detection
+  - image-classification
+  - digital-humanities
+  - ocr
+  - yolo
+  - convnext
 ---
 
-# BOTHROS weights
+# BOTHROS — Aegean sign reading from photographs (Linear A + Linear B)
 
-Unified Aegean sign detector + Linear A / Linear B classifiers. Code, model cards, and benchmarks: https://github.com/jmacdonald263/bothros
+Weights for the [BOTHROS](https://github.com/jmacdonald263/bothros) pipeline:
+photograph an ancient Aegean tablet, get the signs on it by catalogue code and
+reading.
 
-Weights are CC BY-NC-SA 4.0 (derived from research-only corpora).
+- **`yolo_aegean_unified.pt`** — one YOLO11s detector localising signs for *both*
+  scripts (sign detection is class-agnostic; Linear A and Linear B signs are
+  visually cognate).
+- **`la_classifier.pth` / `lb_classifier.pth`** — ConvNeXt-Tiny classifiers
+  (AB-codes for Linear A; B-codes + readings for Linear B).
+- **`lb_class_to_reading.json`** — Linear B B-code → phonetic reading map.
+
+## Results (held-out, leak-free)
+
+| metric | Linear A | Linear B | DeepScribe (cuneiform ref) |
+|---|---|---|---|
+| classifier oracle top-1 | 79.3% | 64.5% | 74% |
+| pipeline E2E sign top-1 | 66.9% | 62.6% | 56.3% |
+| pipeline per-line F1 | 64.9% | 76.5% | — |
+| CER (lower better) | ~0.49 | 0.44 | 0.669 |
+
+## Usage
+```bash
+pip install bothros            # or: pip install -e . from the GitHub repo
+python3 scripts/download_weights.py
+python3 -m bothros read your_tablet.jpg --script la   # or --script lb
+```
+
+## Licence
+**CC BY-NC-SA 4.0** — derived from research-only corpora (GORILA, DĀMOS, SigLA).
+The pipeline source code is MIT (see the GitHub repo). Non-commercial use only.
+
+## Citation
+See https://github.com/jmacdonald263/bothros (Zenodo DOI on release).