Hebrish
Technical

Datasets / Dataset index

English Hebrew Codeswitching ASR Benchmark

Held-out test sets (v1, v2) the models are scored on; never trained on.

Accept terms and download on Hugging Face

Details

Type
Benchmark
Access
Gated, automatic: accept the terms on Hugging Face and access is approved instantly.
Licence
CC BY 4.0
Rows
324
Language
English, Hebrew
Last updated
2026-10-30
DOI
10.57967/hf/11121
Training use
Never (evaluation only)
Hugging Face
Hebrish/English-Hebrew-Codeswitching-ASR-Benchmark

Fields come from the dataset index (built 2026-11-06) and the dataset's Hugging Face card; a field the card does not state is left out. All datasets.