Deep-Learning-for-Audio

Getting Started

Make sure that you have make --version greater than 3.81.

• Cloning the repository:

  git clone https://github.com/khaykingleb/Deep-Learning-for-Audio.git && cd Deep-Learning-for-Audio

• Looking up targets:

  make help

• Training models:

  poetry shell
  python3 -m src.core.<TASK> --config_path=<CONFIG>.yaml

To Be Added

• Attention model for KWS.
• Acoustic model for TTS.
• Vocoder for TTS.