# Low-resource Language Model

TwiBERT is a pre-trained language model specifically designed for the Twi language, widely used in Ghana and West Africa.

MyanBERTa is a Burmese pre-trained language model based on the BERT architecture, pre-trained on a Burmese dataset containing 5,992,299 sentences.

This model is a fine-tuned Nepali speech recognition model based on facebook/wav2vec2-large-xlsr-53.

This is an ELECTRA model designed specifically for Filipino language, used for generating synthetic text and pre-training discriminators.

An Arabic poetry generation model fine-tuned from gpt2-small-arabic, trained on 40,000 Arabic poems from different periods

A Sundanese masked language model based on the RoBERTa architecture, trained on multiple datasets.

Indonesian Small RoBERTa is a masked language model based on the RoBERTa architecture, specifically trained for Indonesian language, suitable for text infilling and feature extraction tasks.

GPT-2 model trained for Turkish text, serving as a starting point for text generation tasks

A Bengali language model pre-trained based on the BERT architecture, supporting masked language modeling tasks