feat: default OCR language to Telugu (te)

2026-07-10 12:28:40 -04:00 · 2026-07-10 12:28:40 -04:00 · 73a5915f4f
parent e68cc23993
commit 73a5915f4f
1 changed files with 2 additions and 1 deletions
--- a/newspaper-extractor/backend/app/pipeline/ocr_engine.py
+++ b/newspaper-extractor/backend/app/pipeline/ocr_engine.py
@ -36,4 +36,5 @@ class OCREngine:

    def detect_language(self, crop):
        # Quick langdetect on a fast English OCR pass, or script detection
-        return "en"  # plug in script-detection model
+        # Hardcoding to 'te' (Telugu) which also supports English numbers/characters
+        return "te"