External/SnapOtter
1
0
Fork 0
mirror of https://github.com/snapotter-hq/SnapOtter.git synced 2026-08-03 07:46:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(ocr): fix PaddleOCR crashes, add multi-image and auto-detect language

Browse Source 
- Pin PaddlePaddle to 3.0.0 on ARM64 to fix segfault in PIR inference
  engine (3.1+ crashes on aarch64 Debian Bookworm)
- Fix text extraction for PaddleOCR 3.4.x result format (rec_texts)
- Add Node.js-level fallback chain (best -> balanced -> fast) when
  Python subprocess crashes
- Add multi-image OCR: processes all uploaded files sequentially with
  per-file progress and filename headers in combined output
- Convert input images to PNG via Sharp before OCR so HEIC, AVIF, WebP,
  TIFF all work transparently
- Implement real auto-detect language using Tesseract multi-lang script
  detection (analyzes Unicode ranges for Hangul, CJK, Kana, Latin)
- Default enhance to off (hurts clean digital images)
This commit is contained in:
Siddharth Kumar Sah
2026-04-12 23:46:39 +08:00
parent f2e17d2d44
commit 29fafd0722
6 changed files with 259 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker/Dockerfile
+1 -1
View File
@@ -127,7 +127,7 @@ RUN if [ "$TARGETARCH" = "amd64" ]; then \
; else \
/opt/venv/bin/pip install "rembg[cpu]==2.0.62" && \
/opt/venv/bin/pip install realesrgan==0.3.0 && \
/opt/venv/bin/pip install paddlepaddle>=3.2.1 "paddleocr[doc-parser]>=3.4.0,<3.5.0" \
/opt/venv/bin/pip install paddlepaddle==3.0.0 "paddleocr[doc-parser]>=3.4.0,<3.5.0" \
; fi
# mediapipe 0.10.21 only has amd64 wheels; arm64 maxes out at 0.10.18