IMS-Toucan

Installation 🦉

Basic Requirements

Python 3.10 is the recommended version.

To install this toolkit, clone it onto the machine you want to use it on (should have at least one cuda enabled GPU if you intend to train models on that machine. For inference, you don't need a GPU).

If you're using Linux, you should have the following packages installed, or install them with apt-get if you haven't (on most distributions they come pre-installed):

libsndfile1
espeak-ng
ffmpeg
libasound-dev
libportaudio2
libsqlite3-dev

Navigate to the directory you have cloned. We recommend creating and activating a virtual environment to install the basic requirements into. The commands below summarize everything you need to do under Linux. If you are running Windows, the second line needs to be changed, please have a look at the venv documentation.

python -m venv <path_to_where_you_want_your_env_to_be>

source <path_to_where_you_want_your_env_to_be>/bin/activate

pip install --no-cache-dir -r requirements.txt

Run the second line everytime you start using the tool again to activate the virtual environment again, if you e.g. logged out in the meantime. To make use of a GPU, you don't need to do anything else on a Linux machine. On a Windows machine, have a look at the official PyTorch website for the install-command that enables GPU support.

Storage configuration

If you don't want the pretrained and trained models as well as the cache files resulting from preprocessing your datasets to be stored in the default subfolders, you can set corresponding directories globally by editing Utility/storage_config.py to suit your needs (the path can be relative to the repository root directory or absolute).

Pretrained Models

You don't need to use pretrained models, but it can speed things up tremendously. They will be downloaded on the fly automatically when they are needed, thanks to Hugging Face🤗 and VB in particular.

[optional] eSpeak-NG

eSpeak-NG is an optional requirement, that handles lots of special cases in many languages, so it's good to have.

On most Linux environments it will be installed already, and if it is not, and you have the sufficient rights, you can install it by simply running

apt-get install espeak-ng

For Windows, they provide a convenient .msi installer file on their GitHub release page. After installation on non-linux systems, you'll also need to tell the phonemizer library where to find your espeak installation by setting the PHONEMIZER_ESPEAK_LIBRARY environment variable, which is discussed in this issue.

For Mac it's unfortunately a lot more complicated. Thanks to Sang Hyun Park, here is a guide for installing it on Mac: For M1 Macs, the most convenient method to install espeak-ng onto your system is via a MacPorts port of espeak-ng. MacPorts itself can be installed from the MacPorts website, which also requires Apple's XCode. Once XCode and MacPorts have been installed, you can install the port of espeak-ng via

sudo port install espeak-ng

As stated in the Windows install instructions, the espeak-ng installation will need to be set as a variable for the phonemizer library. The environment variable is PHONEMIZER_ESPEAK_LIBRARY as given in the GitHub thread linked above. However, the espeak-ng installation file you need to set this variable to is a .dylib file rather than a .dll file on Mac. In order to locate the espeak-ng library file, you can run port contents espeak-ng. The