Spaces:

Pointf5ive
/

Codex_Extractor

Sleeping

App Files Files Community

Codex_Extractor / smoke_signal /scripts

200 kB

Ctrl+K

Ctrl+K

5 contributors

History: 15 commits

Claude

chore: track *.traineddata via LFS + Gill Sans font->model mapping

57311b9 3 months ago

01_register_sources.py

10.2 kB
Upload 13 files 3 months ago
02_profile_pdfs.py

9.82 kB
Create 02_profile_pdfs.py 3 months ago
03_ocr_bakeoff.py

24.1 kB
Fix Smoke Signal Surya OCR for new predictor API 3 months ago
04_region_detector.py

19 kB
Upload 04_region_detector.py 3 months ago
05_llm_normalise.py

19.9 kB
Stages 7+8: LLM normalisation and review workbench 3 months ago
06_review_workbench.py

22.7 kB
Stages 7+8: LLM normalisation and review workbench 3 months ago
07_codex_exporter.py

18.4 kB
Stages 9+10: Codex exporter and validation report 3 months ago
08_validation_report.py

15.5 kB
Stages 9+10: Codex exporter and validation report 3 months ago
09_finetune_surya.py

21.2 kB
Training phase: scripts 09+10, --model flag in 03, gold schema patch 3 months ago
10_recalibrate.py

15.1 kB
Training phase: scripts 09+10, --model flag in 03, gold schema patch 3 months ago
font_library.py

14.6 kB
chore: track *.traineddata via LFS + Gill Sans font->model mapping 3 months ago
punct_corrector.py

9.24 kB
fix: gruffalo lowercase, remove dangerous so->Go word correction 3 months ago