Metadata-Version: 2.4
Name: faas-metric
Version: 0.1.0
Summary: Fairness-Adjusted ASR Score metric
Author: Satyam Rahangdale, Utkarsh Anand, Animesh Mukherjee
Author-email: Anand Rai <raianand.1991@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/SatyamR196/ASR-FairBench
Project-URL: Repository, https://github.com/SatyamR196/ASR-FairBench
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: pandas
Requires-Dist: numpy
Requires-Dist: statsmodels

# faas-metric

`faas-metric` is a Python library that implements the **Fairness-Adjusted ASR Score (FAAS)** — a unified metric to evaluate **both accuracy and fairness** in automatic speech recognition (ASR) systems. Based on the methodology proposed in the paper *ASR-FAIRBENCH: Measuring and Benchmarking Equity Across Speech Recognition Systems*, this library helps researchers and developers quantify model performance disparities across demographic groups using statistical fairness modeling.

...

## 📄 Citation
If you use this package in your work, please cite:
```
@inproceedings{rai2025asrfairbench,
  title={ASR-FAIRBENCH: Measuring and Benchmarking Equity Across Speech Recognition Systems},
  author={Rai, Anand and Rahangdale, Satyam and Anand, Utkarsh and Mukherjee, Animesh},
  booktitle={Proceedings of Interspeech},
  year={2025},
}
```

...
