kurianbenoy/whisper_normalizer

A python package for whisper normalizer

57
/ 100
Established

This tool helps improve the accuracy of speech-to-text systems by standardizing spoken text into a consistent written form. It takes raw text output from an Automatic Speech Recognition (ASR) system and converts it into a normalized version, making it easier to compare and evaluate against ground truth. This is ideal for speech technology researchers and developers working on ASR metrics and model comparisons.

Used by 2 other packages. No commits in the last 6 months. Available on PyPI.

Use this if you need to standardize text for evaluating Automatic Speech Recognition (ASR) systems, especially if you're working with English or Indic languages like Malayalam.

Not ideal if your primary need is for general natural language processing tasks not related to ASR evaluation or if you require normalization for many low-resource languages beyond those specifically supported.

speech-recognition ASR-evaluation natural-language-processing Indic-languages text-standardization
Stale 6m
Maintenance 2 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

76

Forks

17

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 06, 2025

Commits (30d)

0

Dependencies

3

Reverse dependents

2

Get this data via API

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

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