This project is focused on developing a system that can transcribe Wolof speech into English text using a whisper model. Wolof is a language spoken in Senegal, Gambia, and Mauritania, among other West African countries.
- Clone the repository:
git clone https://github.com/lodjim/wolof_speech2english-whisper.git
- Install the required packages:
pip install -r requirements.txt
python main.py train --modelBase <model_base> --path2dataset <path_to_dataset> --outputDir <output_directory> --perDeviceTrainBatchSize <batch_size> --lr <learning_rate>
This project is licensed under the MIT License.