Franck-Dernoncourt/ASR_benchmark

Program to benchmark various speech recognition APIs

36
/ 100
Emerging

This tool helps you evaluate and compare different automated speech recognition (ASR) services by transcribing your audio files and calculating how accurately they perform. You provide audio recordings and their correct text transcripts, and it outputs a performance score (word error rate) for each ASR provider. It's designed for anyone who needs to choose the best ASR service for their specific audio data.

No commits in the last 6 months.

Use this if you need to objectively compare several speech-to-text APIs to determine which one performs best on your unique audio content.

Not ideal if you're looking for an off-the-shelf transcription service rather than a tool to benchmark existing services.

speech-to-text evaluation voice assistant development audio data processing transcription quality ASR selection
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

81

Forks

18

Language

Python

License

Last pushed

Sep 06, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/Franck-Dernoncourt/ASR_benchmark"

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