Low Resource Nlp Python Packages

mteb

MTEB: State-of-the-art evaluation of embeddings across languages and modalities

simplemma

Simple multilingual lemmatizer for Python, especially useful for speed and efficiency

seb

A Scandinavian Benchmark for sentence embeddings

calamancy

NLP pipelines for Tagalog using spaCy

akshara-tokenizer

Akshara-aware tokenizer for six Brahmic scripts, with a trained SentencePiece model

low-resource-nlp-toolkit

Selective language routing and code-switch audits, evaluated on a reproducible AfriSenti benchmark.

telugu-chandassu

Classical Telugu prosody (chandassu) identifier — detects and classifies traditional poetic meters using NLP

rbpe

R-BPE: Improving BPE-Tokenizers with Token Reuse

ne-agent

Terminal AI agent for Northeast India's low-resource languages. Local, offline, multilingual routing (search, translate, transcribe).