Installation

Pre-requisites

Anaconda python: Install the anaconda python distribution (or miniconda). If conda is already installed on your system, make sure you have conda v4.8.4+. If not, update from an older version with conda update conda.

Libsoundfile (Linux only): If you are on Linux and want to load audio from a wide range of audio formats (other than wav), then you need to install libsndfile. The GUI uses the soundfile python package, which relies on libsndfile. libsndfile will be automatically installed on Windows and macOS. On Linux, the library needs to be installed manually with: sudo apt-get install libsndfile1. Again, this is only required if you work with more exotic audio files.

Visual C++ runtime (Windows only): This is typically installed so only required if DAS fails to load the native tensorflow runtime. Download the latest version here.

Install DAS

Create an anaconda environment called das that contains all the required packages:

conda create python=3.8 das -c conda-forge -c ncb -n das

Test the installation (Optional)

To quickly test the installation, run these commands in the terminal:

conda activate das  # activate the conda environment
das train --help  # test DAS training
das gui  # start the DAS GUI

The second command will display the command line arguments for das train. The last command, das gui, will start the GUI. This step will not work with the no-GUI install.

Make a desktop icon (Optional)

To start the DAS GUI without having to use a terminal, create a clickable startup script on the desktop.

On macOS or Linux, place a text file called das.sh (linux) or das.command (macOS) with the following content on your desktop:

# /bin/bash
source $CONDA_PREFIX/etc/profile.d/conda.sh
conda activate das
das gui

Make the files executable with chmod +x FILENAME, where FILENAME is das.sh (linux) or das.command (macOS).

For windows, place a text file called das.bat with the following content on the desktop:

TITLE DAS
CALL conda.bat activate das
das gui

Next steps

If all is working, you can now use DAS to annotate song. To get started, you will first need to train a network on your own data. For that you need annotated audio - either create new annotations using the GUI or convert existing annotations using python scripts.