Skip to main content

Fairness-Adjusted ASR Score metric

Project description

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},
}

...

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

faas_metric-0.1.0.tar.gz (2.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

faas_metric-0.1.0-py3-none-any.whl (2.9 kB view details)

Uploaded Python 3

File details

Details for the file faas_metric-0.1.0.tar.gz.

File metadata

  • Download URL: faas_metric-0.1.0.tar.gz
  • Upload date:
  • Size: 2.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for faas_metric-0.1.0.tar.gz
Algorithm Hash digest
SHA256 eb1821cd363ab86d99b11320d37cdcc80706b6f75e104c6926905bc130320b59
MD5 10671126783e3904c799a90bcb3cb442
BLAKE2b-256 78cadf29332f56a7a565f7601359718b57c861dd9131b3e1733b19deb2c4e9e0

See more details on using hashes here.

File details

Details for the file faas_metric-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: faas_metric-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 2.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.0

File hashes

Hashes for faas_metric-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 88def26d318a45e1e24c664d9eff5bbc759c05a124b91678db114e979b12bf72
MD5 cf54d90d2853e9d4eb5f30662791e0cd
BLAKE2b-256 4421dd771056692f269c63e5d5ab516ff64889c82bc30da1b0c88f46007b70c2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page