jcsilva/asr-benchmark

Benchmark of industrial Speech Recognition systems for Brazilian Portuguese

26
/ 100
Experimental

This project helps researchers and engineers evaluate how well different speech recognition systems perform for Brazilian Portuguese. You input audio files and their correct transcriptions, and it outputs detailed error rates (Word Error Rate and Sentence Error Rate) for popular services like IBM, Microsoft, and Google. It's designed for anyone working with speech technology who needs to compare the accuracy of commercial ASR systems for this specific language.

No commits in the last 6 months.

Use this if you need to objectively compare the performance of different commercial Automatic Speech Recognition (ASR) systems for Brazilian Portuguese audio.

Not ideal if you're looking for a simple, out-of-the-box solution to transcribe audio without needing to benchmark systems, or if your primary interest is in languages other than Brazilian Portuguese (though it can be adapted).

speech-recognition language-technology brazilian-portuguese performance-evaluation audio-processing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

10

Forks

2

Language

Python

License

Last pushed

Aug 21, 2017

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/jcsilva/asr-benchmark"

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