ThetaOne-AI/HiKE

Hierarchical Korean-English Code-Switching Speech Recognition Benchmark (EACL Findings 2026, To Appear) | 한영 혼용 음성인식 벤치마크

34
/ 100
Emerging

This is a benchmark and evaluation tool for assessing how well Automatic Speech Recognition (ASR) models transcribe speech that mixes Korean and English. It takes audio files containing mixed-language speech and outputs detailed error rates, showing where models struggle with word, phrase, or sentence-level code-switching and loanwords. ASR developers and researchers can use this to rigorously test and improve their models' performance on challenging bilingual audio.

Use this if you are developing or evaluating ASR models and need a standardized, high-quality benchmark to measure their accuracy on Korean-English code-switching speech.

Not ideal if you are a casual user simply looking to transcribe Korean-English mixed speech without needing to evaluate model performance or develop new ASR systems.

speech-recognition-development bilingual-ai korean-english-language model-evaluation natural-language-processing-research
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

Apache-2.0

Last pushed

Jan 04, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/ThetaOne-AI/HiKE"

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