This program is a demo
Performance development in progress
Check the visual step by step processing and result in colab: https://colab.research.google.com/drive/1r3CrQwRuvIeA7wbcQPywopv0zOgyOkVE?usp=share_link
For the program, run to install the libs
pip install -r requirements.txt
Run
python main.py
to start the app
If permission error occurs while you are using gdown to download shared files (dataset) from google drive, run this:
!pip install --upgrade --no-cache-dir gdown
There are 184 speakers in the dataset, the train/test set split ratio is 7:3, and the model gets 92% accuracy on the test set