Skip to content

Latest commit

 

History

History
38 lines (24 loc) · 733 Bytes

README.md

File metadata and controls

38 lines (24 loc) · 733 Bytes

Portuguese Variety Identifier

A classifier for distinguishing between European and Brazilian Portuguese.

Development Environment

1. Set Up a Virtual Environment

To create a virtual environment using Conda, run the following commands:

conda create --name .conda python=3.11
conda activate .conda

2. Install Dependencies

Install the necessary dependencies by running:

pip install -e .

Training

Training scripts are located in the train folder. For example, to find the best hyperparameters for the BERT model, run:

sh scripts/train/search_bert.sh

Evaluation

To evaluate the trained models, execute the evaluation script:

sh scripts/eval/run.sh