analyticsinmotion/werx

🐍📦 Easy-to-use Python package for lightning-fast Word Error Rate (WER) analysis

47
/ 100
Emerging

This tool helps you quickly assess the accuracy of text transcription systems, like those used in voice-to-text applications or call center analytics. You input the correct version of what was said (reference text) and the system's transcribed output, and it calculates how many words were wrong. This is for data scientists, speech engineers, or researchers who need to evaluate and compare transcription quality efficiently.

Used by 1 other package. Available on PyPI.

Use this if you need to rapidly calculate the Word Error Rate (WER) for large volumes of transcribed text to evaluate speech-to-text models or similar systems.

Not ideal if you're looking for a full natural language processing toolkit for text analysis beyond error rate calculation.

speech-to-text transcription-quality voice-recognition language-technology audio-analytics
Maintenance 10 / 25
Adoption 5 / 25
Maturity 24 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/analyticsinmotion/werx"

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