kahne/fastwer

A PyPI package for fast word/character error rate (WER/CER) calculation

62
/ 100
Established

This tool helps speech scientists and researchers quickly evaluate the accuracy of their speech-to-text systems. You provide the text output from your system (hypothesis) and the correct, human-transcribed text (reference). It then calculates how many words or characters are incorrect, either for individual sentences or for an entire collection of text, providing a clear error rate.

Available on PyPI.

Use this if you need to rapidly quantify the performance of a speech recognition model by comparing its output against ground-truth transcripts.

Not ideal if you need advanced linguistic analysis or more complex metric visualizations beyond standard word and character error rates.

speech-recognition natural-language-processing audio-transcription model-evaluation
Maintenance 10 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 18 / 25

How are scores calculated?

Stars

70

Forks

16

Language

Python

License

MIT

Last pushed

Feb 13, 2026

Commits (30d)

0

Dependencies

1

Get this data via API

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

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