prosperious commited on
Commit
c630d08
·
verified ·
1 Parent(s): e97a26e

Add archive card

Browse files
Files changed (1) hide show
  1. README.md +23 -0
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: mixed-see-readme
4
+ tags: [ocr, archive]
5
+ ---
6
+
7
+ # OCR projects archive
8
+
9
+ This is a private archive of the smaller OCR projects from `~/ocr` on the OCR server, migrated on 16 Nov 2026.
10
+
11
+ | Folder | What |
12
+ |---|---|
13
+ | `OCR_INDRA/` | Indra OCR investigation: code, docs, results, reports, and the git history (sharded). **Indra weights (`models/`) and Indra fine-tunes (`runs/`) are left out** because the AI PUBS OpenRAIL-M licence has commercial limits; get the base model from Datalab instead. The 10.5 GB of installed packages (`.deps`, `.torch-cu126`) are also left out. |
14
+ | `ocr-tech/` | OCR for the languages of Nepal (Limbu Sirijonga, Newar, Nepali), including git history. Also on GitHub as `Ampixa/ocr-tech`. |
15
+ | `ocr-tech-mps-integration/` | The MPS integration branch of ocr-tech |
16
+ | `k2-ampixa-demo-ocr/` | Demo app workers and their model cache |
17
+ | `ocr-deva-eval-20260924/` | Newar and smoke evaluation sets with predictions |
18
+ | `jobs/`, `logs/` | Job scripts and logs |
19
+ | `indra_nepali_exp.bundle` | A git bundle of the OCR_INDRA experiment code |
20
+
21
+ Also left out: `paddlex-official-models/` (official PaddleX downloads: PaddleOCR-VL-1.6, PP-DocLayoutV3, PP-OCRv5/v6 det, UVDoc, devanagari_PP-OCRv5_mobile_rec, PP-LCNet orientation models) and `bin/` (the `uv` tool).
22
+
23
+ Folders with many small files, and every `.git` folder, are packed into ~1 GB tar shards, each with a sha256 index.