low-resource-nlp
MTEB: State-of-the-art evaluation of embeddings across languages and modalities
Simple multilingual lemmatizer for Python, especially useful for speed and efficiency
Terminal AI agent for Northeast India's low-resource languages. Local, offline, multilingual routing (search, translate, transcribe).
A Scandinavian Benchmark for sentence embeddings
NLP pipelines for Tagalog using spaCy
A Python toolkit for African language pre-processing, emotion labels, evaluation, and routing.
R-BPE: Improving BPE-Tokenizers with Token Reuse
