Pinned Loading

1. Punjabi_Stemmer Punjabi_Stemmer Public

   Developed a hybrid rule-based and dictionary-enhanced stemmer with over 300 morphological rules and a 50,000+ word dictionary to accurately process Punjabi language morphology. Designed to reduce o…

   Python 2

2. punjabi-gpt-scratch-20m punjabi-gpt-scratch-20m Public

   Developed and pre-trained a 20.39M-parameter Punjabi GPT-style base model from scratch, including corpus preparation, tokenizer training, benchmark evaluation, and text generation, using a cleaned …

   Jupyter Notebook 2

3. Punjabi_Stopwords Punjabi_Stopwords Public

   Developed and curated a comprehensive Punjabi stopwords set to enhance NLP model relevance and preprocessing efficiency. Supports stopword identification, removal, and customization for diverse Pun…

   Python 1

4. ocrguru ocrguru Public

   ocrguru is a simple, extensible CLI wrapper around the Docling OCR toolkit, enabling you to perform OCR on PDFs or images with minimal setup. It bundles multiple open-source engines—EasyOCR, Tesser…

   Python