powerset-calibration 0.1.3

Companion package to the 'On the calibration of powerset speaker diarization models' paper published at Interspeech 2024.

powerset_calibration

This package contains the code used to perform the experiments conducted in the paper 'On the calibration of powerset speaker diarization models' published at Interspeech 2024.

• 📄 Browse the original paper repository
• 📘 Read the docs

This package builds upon the pyannote suite, and thus heavily depends on pyannote.audio, pyannote.core and pyannote.database functionalities.

Installing

🐍 Using pip

pip install powerset_calibration

🏠 Using a local installation

git clone https://github.com/FrenchKrab/powerset_calibration
pip install -e powerset_calibration

Usage

Most of the functionalities of the library are easy to access and just require you to plug in the right parameters.

⏯️ Notebook

To learn how to use this library, please refer to the notebooks which should give you 90% of the informations you need.

• Essential features
  • A1_model_inference: Generate and evaluate an 'inference file' from your segmentation model
  • A2_active_learning_protocol: Create subsets from an existing protocol using active learning-like criterions (e.g. select the 10% least confident data)
• Advanced usage
  • B1_subset_one_file: Manually do all the steps to find the regions of interest in one file (instead of relying on ActiveLearningProtocol).

📘 Documentation

If you want more detail about function/method arguments, please refer to the documentation: https://frenchkrab.github.io/powerset_calibration