stefantaubert/mean-opinion-score

Python library for calculating the mean opinion score and 95% confidence interval of the standard deviation of text-to-speech ratings according to Ribeiro et al. (2011).

36
/ 100
Emerging

This tool helps researchers and evaluators in speech technology analyze the quality of text-to-speech (TTS) systems. You input raw opinion ratings from human evaluators on different TTS samples. It then calculates the Mean Opinion Score (MOS) and its 95% confidence interval, providing a reliable measure of perceived speech quality. This is ideal for speech scientists and NLP researchers assessing TTS models.

Used by 1 other package. No commits in the last 6 months. Available on PyPI.

Use this if you need to objectively quantify the perceived quality of synthetic speech by calculating the Mean Opinion Score and its confidence interval from human listening test data.

Not ideal if you are looking for a tool to conduct the listening tests themselves or to analyze audio quality metrics other than MOS.

speech-technology-evaluation text-to-speech-assessment audio-quality-measurement user-perception-studies
Stale 6m
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 4 / 25

How are scores calculated?

Stars

24

Forks

1

Language

Python

License

MIT

Last pushed

Jan 31, 2025

Commits (30d)

0

Dependencies

2

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/stefantaubert/mean-opinion-score"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.