Hugging Face's logo

Spaces:
phucsd
/
cham-ocr-studio
Running

App Files Community
cham-ocr-studio

Commit History

  1. fix(generator): add missing PIL ImageFont imports and install git in Dockerfile Running

    phucsd
    Verified signature
    4df8b27

  2. feat(studio): set Cham V24 as default model and temporarily hide V25

    phucsd
    Verified signature
    c81c228

  1. feat(keyboard): optimize Cham virtual keyboard with compact 5-row layout and multi-layout selector

    phucsd
    Verified signature
    d9e8ca5

  2. Upload folder using huggingface_hub

    phucsd
    Verified signature
    770f650

  3. Upload folder using huggingface_hub (part 2)

    phucsd
    Verified signature
    ff22b96

  4. Upload folder using huggingface_hub

    phucsd
    Verified signature
    dff7ab3

  5. Upload RESEARCH.md with huggingface_hub

    phucsd
    Verified signature
    075f0d0

  6. Upload README_VI.md with huggingface_hub

    phucsd
    Verified signature
    1fdacdd

  7. Upload README.md with huggingface_hub

    phucsd
    Verified signature
    7c4cdd3

  8. Upload Dockerfile with huggingface_hub

    phucsd
    Verified signature
    3f98804

  1. feat(contact): add phucsd@gmail.com contact across docs and Studio UI

    phucsd
    Verified signature
    ff927bf

  2. docs(academic): freeze active V25 experiment assets and calibrate documentation

    phucsd
    Verified signature
    5a55f05

  3. docs(audit): complete academic precision and reproducibility cleanup

    phucsd
    Verified signature
    efd2c7f

  4. docs(audit): complete academic precision and reproducibility cleanup

    phucsd
    Verified signature
    decc7d3

  5. feat(ocr): integrate dedicated Vietnamese PP-OCRv5 model and streamline dropdown

    phucsd
    Verified signature
    a42bbb0

  6. fix(ui): add scroll offset for sticky header in research TOC and fix sec3-3 heading

    phucsd
    Verified signature
    019892c

  7. fix(audit): refine DOIs, 2025 MTAP title, SEADL attribution, font bundling, and Unicode final VA

    phucsd
    Verified signature
    52b2e03

  8. docs(audit): reconcile academic rigor, ground-truth benchmarks, and official Unicode standards

    phucsd
    Verified signature
    d6a7310

  9. docs(audit): reconcile academic rigor, ground-truth benchmarks, and official Unicode standards

    phucsd
    Verified signature
    1e83cc1

  10. feat(studio): deploy academic English UI, 7-tab research methodology, dual-language docs & GitHub integration

    phucsd
    Verified signature
    5c8462b

  11. feat(studio): deploy academic English UI, 7-tab research methodology, dual-language docs & GitHub integration

    phucsd
    Verified signature
    eda958a

  12. feat(studio): deploy academic English UI, 7-tab research methodology, dual-language docs & GitHub integration

    phucsd
    Verified signature
    2e53a82

  1. Upload folder using huggingface_hub

    phucsd
    Verified signature
    39947d8

  2. Upload folder using huggingface_hub

    phucsd
    Verified signature
    75b8dbb

  3. Upload folder using huggingface_hub (part 2)

    phucsd
    Verified signature
    66e54af

  4. Upload folder using huggingface_hub

    phucsd
    Verified signature
    c826059

  5. feat(studio): deploy specialized Cham-DBNet detector (F1 99.60%)

    phucsd
    Verified signature
    d521e8d

  1. feat(studio): simplify UI by standardizing on DBNet text segmentation

    phucsd
    Verified signature
    2b1771c

  2. fix(studio): make albumentations optional in generate_data.py and trigger rebuild

    phucsd
    Verified signature
    74c9539

  3. fix(studio): add legacy inference.pdmodel for V24 and trigger rebuild

    phucsd
    Verified signature
    0a99ae6

  4. feat(studio): deploy Cham OCR Model V24 (98.64% acc, stanza prefixes & double danda fixes)

    phucsd
    Verified signature
    b863538

  1. chore: trigger rebuild with latest app.py

    phucsd
    Verified signature
    ff97e30

  2. fix: initialize profiler_dict for DBNet and safe base64 decode

    phucsd
    Verified signature
    54ab8cf

  3. feat: integrate PaddleOCR DBNet detection into Studio

    phucsd
    Verified signature
    00d1f28

  1. fix(studio): prioritize coords for vertical bbox, connect corrections API, remove duplicate renderQueue

    phucsd
    Verified signature
    ea34d56

  2. fix(studio): resolve crash on empty coords, Cham unicode block, and safe NMS

    phucsd
    Verified signature
    3ecd16a

  3. fix: update typography schema in DESIGN.md

    phucsd
    Verified signature
    a982603

  4. Upload folder using huggingface_hub

    phucsd
    Verified signature
    a183ff9

  5. Upload folder using huggingface_hub (part 4)

    phucsd
    Verified signature
    2704c2c

  6. Upload folder using huggingface_hub (part 3)

    phucsd
    Verified signature
    732c30f

  7. Upload folder using huggingface_hub (part 2)

    phucsd
    Verified signature
    1f1d9f5

  8. Upload folder using huggingface_hub

    phucsd
    Verified signature
    9a64e3b

  9. Upload README.md with huggingface_hub

    phucsd
    Verified signature
    4873906

  10. Upload Dockerfile with huggingface_hub

    phucsd
    Verified signature
    e3c573d

  11. clean: remove old ocr_training folder

    phucsd
    Verified signature
    5ea8f15

  12. clean: remove legacy ocr_webapp folder

    phucsd
    Verified signature
    3ef6790

  1. Research-backed adaptive clustering: calibrate median_line_height and outlier_gap to prune parchment handle specks [bbox=343..702]

    phucsd
    Verified signature
    cde6afc

  1. Re-assign connected components after true_core_coords deduplication to capture main consonants [ymin=30, ymax=78]

    phucsd
    Verified signature
    2577228

  1. Fix frontend bbox top override to use ymin directly from backend bbox

    phucsd
    Verified signature
    13df67f

  2. Strict background artwork line pruning to eliminate spurious bboxes

    phucsd
    Verified signature
    0ceee51