ThetaOne-AI/HiKE
Hierarchical Korean-English Code-Switching Speech Recognition Benchmark (EACL Findings 2026, To Appear) | 한영 혼용 음성인식 벤치마크
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.
Stars
9
Forks
1
Language
Python
License
Apache-2.0
Category
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.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project