From 73a5915f4f9ab3386a78779ef4d898851032a014 Mon Sep 17 00:00:00 2001 From: Deep Koluguri Date: Fri, 10 Jul 2026 12:28:40 -0400 Subject: [PATCH] feat: default OCR language to Telugu (te) --- newspaper-extractor/backend/app/pipeline/ocr_engine.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/newspaper-extractor/backend/app/pipeline/ocr_engine.py b/newspaper-extractor/backend/app/pipeline/ocr_engine.py index 66bab99..1418aa3 100644 --- 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"