VivekanandaAI / requirements_ocr.txt
jyotirmoy05's picture
Upload 8 files
e889148 verified
raw
history blame contribute delete
394 Bytes
# OCR and PDF processing dependencies
pytesseract==0.3.10
Pillow==10.0.1
PyMuPDF==1.23.8
opencv-python==4.8.1.78
pdf2image==1.16.3
python-dotenv==1.0.0
# Tesseract OCR engine (install system-wide)
# On macOS: brew install tesseract
# On Ubuntu: sudo apt-get install tesseract-ocr
# Additional dependencies for text processing
nltk==3.8.1
spacy==3.7.2
# python -m spacy download en_core_web_sm