5 papers
Amadeus-Verbo Technical Report: The powerful Qwen2.5 family models trained in Portuguese
William Alberto Cruz-Castañeda, Marcellus Amadeus
This report introduces the experience of developing Amadeus Verbo, a family of large language models for Brazilian Portuguese. To handle diverse use cases, Amadeus Verbo includes b…
Evaluation Metrics for Text Data Augmentation in NLP
Marcellus Amadeus, William Alberto Cruz Castañeda
Recent surveys on data augmentation for natural language processing have reported different techniques and advancements in the field. Several frameworks, tools, and repositories pr…
Phonetically rich corpus construction for a low-resourced language
Marcellus Amadeus, William Alberto Cruz Castañeda, Wilmer Lobato +1
Speech technologies rely on capturing a speaker's voice variability while obtaining comprehensive language information. Textual prompts and sentence selection methods have been pro…
Image captioning for Brazilian Portuguese using GRIT model
Rafael Silva de Alencar, William Alberto Cruz Castañeda, Marcellus Amadeus
This work presents the early development of a model of image captioning for the Brazilian Portuguese language. We used the GRIT (Grid - and Region-based Image captioning Transforme…
An Inpainting-Infused Pipeline for Attire and Background Replacement
Felipe Rodrigues Perche-Mahlow, André Felipe-Zanella, William Alberto Cruz-Castañeda +1
In recent years, groundbreaking advancements in Generative Artificial Intelligence (GenAI) have triggered a transformative paradigm shift, significantly influencing various domains…