# Low-Resource Language Processing

This model is a text summarization generation model fine-tuned on the Bodo legal summarization dataset based on facebook/bart-large

This model creates sentence embeddings for Ancient Greek and English texts in a shared vector space, based on an improved HLM architecture and trained through multilingual knowledge distillation.

A fine-tuned Romanized Telugu speech recognition model based on openai/whisper-large-v3

This is a Burmese text generation model based on the Transformer architecture, supporting various text generation tasks.

MizBERT is a masked language model (MLM) pre-trained on Mizo text corpora, utilizing the BERT architecture to effectively learn contextual representations of Mizo vocabulary.

A model supporting multiple languages, with special focus on minority languages in Africa, Asia, and Europe.

SERENGETI is a large-scale multilingual pre-trained model covering 517 African languages and dialects, focusing on bridging the gap in technological resources for African languages.

This is a translation model trained from scratch on an unknown dataset, supporting English to Nahuatl translation tasks.

This is an IndicSBERT model trained on STS datasets of ten major Indian languages, suitable for English and multiple Indian languages with cross-lingual capabilities.

BERTovski is a large pre-trained language model based on Bulgarian and Macedonian texts, utilizing the RoBERTa architecture, and is a product of the MaCoCu project.

A multilingual abstractive summarization model fine-tuned based on google/mt5-base, supporting Arabic, Spanish, and Amharic summarization tasks

A multilingual model supporting French and Bambara, with unspecified specific uses and functions

Arabic to English translation model trained on open subtitle datasets

A pre-trained tiny BERT model for Guarani, trained on Wikipedia and Wiktionary data

A Malayalam speech recognition model fine-tuned based on facebook/wav2vec2-xls-r-300m

Tigrinya sentiment analysis model fine-tuned based on TiELECTRA small model

TajBERTo is the first RoBERTa-like language model for the Tajik language, specifically designed for Tajik natural language processing tasks.

A named entity recognition model for 9 African languages, based on fine-tuned BERT base model

This is a Rundi-to-German machine translation model based on the Transformer architecture, developed by the Helsinki-NLP team.

A Tswana language model pretrained with the Masked Language Modeling (MLM) objective.