symblai/speech-recognition-evaluation

Evaluate results from ASR/Speech-to-Text quickly

47
/ 100
Emerging

Computes Word Error Rate (WER), Word Information Loss (WIL), and Levenshtein distance to benchmark ASR output against reference transcripts, with configurable text normalization (speaker removal, punctuation stripping, lowercasing, etc.). The CLI tool processes plain text files and optionally generates word/phrase-level difference reports, statistics, and color-highlighted visual comparisons. Built as a Node.js utility targeting developers integrating any STT/ASR system who need quick accuracy evaluation without external dependencies.

No commits in the last 6 months. Available on npm.

Stale 6m
Maintenance 0 / 25
Adoption 7 / 25
Maturity 25 / 25
Community 15 / 25

How are scores calculated?

Stars

41

Forks

7

Language

JavaScript

License

Apache-2.0

Last pushed

Dec 28, 2021

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/symblai/speech-recognition-evaluation"

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