Add archive card
Browse files
README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: internal
|
| 4 |
+
language: [ne, en]
|
| 5 |
+
tags: [ocr, document-parsing, nepali]
|
| 6 |
+
---
|
| 7 |
+
|
| 8 |
+
# ocr-tech-k2 (archive)
|
| 9 |
+
|
| 10 |
+
This is a private archive of the hybrid Nepali and English OCR and document-structure toolkit (`ocr-tech` K2 branch), migrated on 16 Nov 2026 from `~/ocr/ocr-tech-k2` on the OCR server. It contains the source (`src/`, `scripts/`, `configs/`, `tests/`), 20 trained models in `runs/hf-*` (`model.safetensors`) together with the Paddle bundles, benchmark outputs and data.
|
| 11 |
+
|
| 12 |
+
**Left out:** training state (`optimizer.pt`, `scheduler.pt`, `rng_state.pth`). The checkpoints load for inference and fine-tuning, but a run can't be resumed exactly where it stopped.
|
| 13 |
+
|
| 14 |
+
**Format.** `outputs/` and `data/` hold many small files, so they are packed into ~1 GB tar shards, each with a sha256 index (`*.index.json`).
|