uiuc-sst/asr24

24-hour Automatic Speech Recognition

39
/ 100
Emerging

This project helps researchers and language experts quickly transcribe spoken audio in a new, unfamiliar language. You provide recordings in the target language along with text data and a pronunciation guide for that language. The output is a transcription of the audio, enabling efficient analysis of spoken content in new languages, especially useful for language preservation, linguistic studies, or intelligence analysis.

No commits in the last 6 months.

Use this if you need to rapidly build an automatic speech recognition system for a low-resource or 'surprise' language and transcribe large amounts of audio.

Not ideal if you primarily need to transcribe common languages for which off-the-shelf ASR models are readily available, as this project focuses on adapting to new languages.

linguistics speech-transcription language-research audio-analysis low-resource-languages
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

27

Forks

7

Language

C++

License

GPL-3.0

Last pushed

Jun 04, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/uiuc-sst/asr24"

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