Scikit-talk is an open-source toolkit for processing collections of real-world conversational speech in Python. The toolkit aims to facilitate the exploration of large collections of transcriptions and annotations of conversational interaction.
Scikit-talk is an open-source toolkit for processing collections of real-world conversational speech in Python. The toolkit aims to facilitate the exploration of large collections of transcriptions and annotations of conversational interaction.
Scikit-talk can be installed from PyPI:
python3 -m pip install scikit-talk
Alternatively, you can install the latest development version from GitHub:
git clone git@github.com:elpaco-escience/scikit-talk.git
cd scikit-talk
python3 -m pip install .
The user documentation can be found here. To read more about the aims of this software, this paper by Liesenfeld et al. (2021) describes the project in detail.
If you want to contribute to the development of scikit-talk, have a look at the contribution guidelines.
Detailed technical information on how to work with the code base can be found in README.dev.md.
This package was created with Cookiecutter and the NLeSC/python-template.
Diversity-aware language technology for conversational data