requirements.txt

gradio==4.29.0  # For the Gradio interface
gTTS==2.2.3  # For text-to-speech
fpdf==1.7.2  # For PDF generation
pdfminer.six==20221105  # For extracting text from PDFs
pdf2image==1.16.3  # For converting PDF pages to images
bert-extractive-summarizer==0.10.1  # For extractive text summarization
sacremoses==0.0.53  # For tokenizer in the transformers library
nltk==3.8.1  # For natural language processing (tokenization, etc.)
yake==0.4.8  # For keyword extraction
pytesseract==0.3.8  # For OCR, but note that tesseract binary is required
transformers==4.29.0  # Specifying a version that is available
torch==2.0.0  # PyTorch for deep learning models
python-docx==0.8.11  # For handling .docx files