This repo is created for the exam project of the course Automatic Speach Recognition ( LET-REMA-LCEX10). The goal, its structure, and its results are elaborated upon in the corresponding paper.
In short: the goal of the project is to try to train a Recurrent Neural Network on an artifically created dataset of concurrent speakers. We tested performance on different levels.
- Install Poetry:
pip install poetry
- Run
poetry install
to install the virtual environment - Run
poetry python main.py
to run the project. Choose which tasks to run by changing the variable at the top of the file. - [Optional] Run
poetry shell
to enter the virtual environment