Fix Docker heredoc for NVIDIA libs

Fix cuDNN runtime wiring for Paddle GPU

Install Paddle GPU from PyPI for HF

Use slim GPU wheel image for HF rollout

Enable GPU OCR in full HF app

Deploy full studio app to HF

Deploy updated core backend pipeline

Allow core mode without local web assets

Split OCR core from local studio and deploy HF core

Update Dockerfile and app.py

Update gitignore

Upload folder using huggingface_hub

Change text for README file

Change text for README file

Upload folder using huggingface_hub

Upload folder using huggingface_hub

Use local PaddleOCR models

Switch paddlepaddle to 2.6.2

Switch to Docker with Python 3.10

Fix filename handling in HF demo; switch input to gr.File; ensure correct file reading and export to Excel

Fix Gradio output

Add filename and title export to Excel; update hf_process to build DataFrame from title + sensors; improve file name handling

Fix ocr code

Fix ocr code

Fix ocr code

Add print of results

Add print of sensors

Add print of sensors

Fix ocr_sensors function

Fix ocr_sensors function

Add print for roi and ocr_results

Add print for roi and ocr_results

Fix app.py

Fix app.py

Fix app.py

Fix pipeline code for OCR ensors

Fix OCR sensors: remove forced ROI height clamp (hh=17) causing unreadable ROIs

Update requirements: numpy, opencv, gradio, easyocr

Replace Tesseract with EasyOCR for title only

Replace Tesseract with EasyOCR for title only

Add pytesseract log

Add apt.txt with tesseract dependencies

fix: correct color ranges

fix: correct color ranges parsing

Add import pytesseract

Update demo pipeline

downgrade numpy to 1.23.5 for PaddleOCR

Fix color

Fix sdk version

use gradio 3.41.2 for HF compatibility