Popular GitHub Repositories for Low Resource Languages

Open-source benchmark datasets and pretrained transformer models in the Filipino language.

Speech synthesis (TTS) in low-resource languages by training from scratch with Fastpitch and fine-tuning with HifiGan

NLP pipelines for Tagalog using spaCy

Exploring the Limits of Low-Resource Neural Machine Translation

The EveryVoice TTS Toolkit - Text To Speech for your language

Repository for multilingual speech data resources for native languages of Zambia.

Generate synthetic labeled data for extremely low-resource languages using bilingual lexicons.

Minangkabau NLP corpus. PACLIC 2020

Low resource machine translation using Transformers and Iterative Back translation

Graph Convolutional Network for Swahili News Classification: https://arxiv.org/abs/2103.09325

Dynamic Transfer Learning for Low-Resource Neural Machine Translation

This project explores zero-shot emotional speech synthesis using EMOD, a novel approach combining emotion and content embeddings for multilingual and cross-lingual emotion transfer. Built on a VITS-based TTS model, it preserves speaker identity while enhancing expressiveness, enabling emotion transfer across languages and genders efficiently.

Code + data for the EMNLP'20 publication "Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages"

Evaluation of Open and Closed-Source Multi-lingual LLMs for Low-Resource Bangla Language

Code for AACL23 paper "Benchmarking Procedural Language Understanding for Low-Resource Languages: A Case Study on Turkish"

This repository highlights the LLMs reasoning capabilities of ? Mistral / LLaMA-3 / Phi-3 / Gemma / Flan-T5 / GPT-4o ? in Targeted Sentiment Analysis in Russian / Translated to English mass-media ?

Analysis of LLM token representation of texts in different languages

A natural language processing and machine learning project for a low resource langauge in Zambia.

Open-Ended Text Generation in isiZulu: Decoding Strategies for a Morphologically Rich Low-Resource Language