BagratMinasyan/armenian_text_embedding_demo
A demonstration repository for a pre-trained Armenian text embedding model, showcasing applications in text classification, keyword extraction, topic modeling, and product search via Jupyter notebooks and a Gradio interface.
AzgIntel is an AI-powered NLP pipeline for Armenian text classification using a BERT-based multilingual model. It pro...
A specialized evaluation benchmark for testing text embedding models on Armenian language tasks including semantic te...
A Python package for clustering and deduplicating Armenian news articles using NLP and machine learning techniques. I...
A project to create a bilingual Western Armenian-English large language model using QLoRA fine-tuning on Qwen 2.5 1.5...
A student project implementing multiple tokenization methods (BPE, WordPiece, SentencePiece, tiktoken) for Armenian l...
A Western Armenian language model project using transformer architecture, implemented in Jupyter notebooks. Includes ...