---
language:
- bo
license: apache-2.0
tags:
- image-classification
- tibetan
- uchen
- ume
- script-classification
- dinov3
- fine-tuned
library_name: transformers
pipeline_tag: image-classification
base_model: facebook/dinov3-vits16-pretrain-lvd1689m
datasets:
- openpecha/uchen_ume_classification_dataset
metrics:
- f1
- accuracy
model-index:
- name: Uchen-Ume Classifier (DINOv3 ViT-S) — center crop
  results:
  - task:
      type: image-classification
      name: Tibetan Script Classification (center-crop whole page)
    dataset:
      name: openpecha/uchen-ume-classification-benchmark
      type: openpecha/uchen-ume-classification-benchmark
      split: test
    metrics:
    - name: Macro F1 (center crop)
      type: f1
      value: 0.983
    - name: Accuracy (center crop)
      type: accuracy
      value: 0.993
- name: Uchen-Ume Classifier (DINOv3 ViT-S) — full page
  results:
  - task:
      type: image-classification
      name: Tibetan Script Classification (full page)
    dataset:
      name: openpecha/uchen-ume-classification-benchmark
      type: openpecha/uchen-ume-classification-benchmark
      split: test
    metrics:
    - name: Macro F1 (full page)
      type: f1
      value: 0.708
    - name: Accuracy (full page)
      type: accuracy
      value: 0.807
---

# Uchen vs Umê Classifier (DINOv3 ViT-S)

Binary Tibetan script classifier: **Uchen** (དབུ་ཅན།, headed/printed script) vs **Umê** (དབུ་མེད།, headless/cursive script). Fine-tuned from [DINOv3 ViT-S](https://huggingface.co/facebook/dinov3-vits16-pretrain-lvd1689m) on ~10,000 manuscript scans from the [Buddhist Digital Resource Center](https://www.bdrc.io) (BDRC).

**Dataset:** [openpecha/uchen-ume-classification-dataset](https://huggingface.co/datasets/openpecha/uchen-ume-classification-dataset)

## Which checkpoint to use

Pick the variant that matches **how you preprocess at inference**:

| Your pipeline | Weights | Inference preprocess |
|---------------|---------|----------------------|
| **Center-crop whole page** (resize short edge → 224, center crop) | **`center_crop_all/final_model.pt`** | `--preprocess center_crop_whole_page` |
| **Raw full manuscript page** (no PIL crop before DINO) | **`without_preprocess/final_model.pt`** | `--preprocess none` |

**Do not** use `with_preprocess/` — it was trained with center crop on train/val but evaluated on full-page test (56% acc). That train/test mismatch is why val looked ~99% while test JSON was ~56%.

## Best results

Hub split: 9,110 train / 1,000 val / 851 test (work-stratified).

| Variant | Train | Val | Test @ eval | Test acc | Test macro-F1 | Val macro-F1 (best) |
|---------|-------|-----|-------------|:--------:|:-------------:|:-------------------:|
| **`center_crop_all/`** | center crop | center crop | **center crop** | **99.3%** | **0.983** | **0.996** |
| **`without_preprocess/`** | none | none | none (full page) | **80.7%** | **0.708** | 0.771 |

### Test confusion matrices (851 pages)

| Variant | uchen→uchen | uchen→ume | ume→uchen | ume→ume |
|---------|------------:|----------:|----------:|--------:|
| **`center_crop_all/`** | 94 | 3 | 3 | 751 |
| **`without_preprocess/`** | 97 | 2 | 165 | 603 |

See `confusion_matrix.json` and `confusion_matrix.png` in each variant folder on the Hub.

## Training data

| Class | Train | Validation | Test | Total |
|-------|------:|-----------:|-----:|------:|
| Uchen | ~3,124 | ~340 | ~290 | ~3,754 |
| Ume | ~5,986 | ~660 | ~561 | ~7,207 |
| **Total pages** | **9,110** | **1,000** | **851** | **10,961** |

Splits are partitioned at the **work level** — all pages from the same manuscript stay in one split only.

## Architecture

- **Backbone:** DINOv3 ViT-S/16 (21M params)
- **Head:** LayerNorm → Dropout(0.1) → Linear(384, 128) → GELU → Dropout(0.1) → Linear(128, 2)
- **Stages:** A (head) → B (last 2 blocks) → C (last 4 blocks)
- **Balancing:** WeightedRandomSampler + class-weighted cross-entropy

## Quick start

### Center-crop pipeline (recommended if you crop pages)

```python
from huggingface_hub import hf_hub_download
import torch

path = hf_hub_download(
    "openpecha/uchen-ume-classifier",
    "center_crop_all/final_model.pt",
    repo_type="model",
)
ckpt = torch.load(path, map_location="cpu", weights_only=False)
```

```bash
python inference_uchen_ume.py \
  --image page.jpg \
  --weights center_crop_all/final_model.pt \
  --preprocess center_crop_whole_page
```

### Full-page pipeline

```python
path = hf_hub_download(
    "openpecha/uchen-ume-classifier",
    "without_preprocess/final_model.pt",
    repo_type="model",
)
```

```bash
python inference_uchen_ume.py \
  --weights without_preprocess/final_model.pt \
  --preprocess none
```

## Repo layout

```
center_crop_all/             ← center_crop_whole_page at inference (~99% test)
  final_model.pt
  model_card.json
  results.json               ← includes confusion_matrix
  confusion_matrix.json
  confusion_matrix.png
without_preprocess/          ← full pages (~81% test)
  final_model.pt
  model_card.json
  results.json
  confusion_matrix.json
  confusion_matrix.png
```

## Limitations

- **Preprocess must match training.** Center-crop model on full pages ≈ 56%; full-page model expects uncropped input.
- Trained on BDRC digitised manuscripts; may underperform on photos or non-BDRC scans.
- **Access requirement:** DINOv3 is gated — accept [facebook/dinov3-vits16-pretrain-lvd1689m](https://huggingface.co/facebook/dinov3-vits16-pretrain-lvd1689m) and run `huggingface-cli login`.

## Citation

```bibtex
@misc{karma2026uchenume,
    title        = {Uchen-Ume Classifier: Binary Tibetan Script Classification with DINOv3},
    author       = {Karma Tashi and Elie Roux},
    year         = {2026},
    publisher    = {HuggingFace},
    url          = {https://huggingface.co/openpecha/uchen-ume-classifier},
    note         = {Funded by Khyentse Foundation. Images sourced from the Buddhist Digital Resource Center (BDRC).}
}
```

## Acknowledgements

Developed by **Dharmaduta** for the **[Buddhist Digital Resource Center](https://www.bdrc.io)** (BDRC) Etext Corpus project, with funding from the **Khyentse Foundation**. Annotation guidelines by **Pentsok Rtsang**.