AI · Collection
Code Switching (English And Hebrew) - All Resources
Datasets and fine tunes (mine) focused on English (primary) with Hebrew code-switching. Targeted use-case: improved ASR accuracy among olim
5 spaces · 4 models · 4 datasets
- model danielrosehill/Parakeet-TDT-0.6B-v2-English-Hebrew-Codeswitching Parakeet V2 fine-tuned for English/Hebrew code-switching
- dataset danielrosehill/English-Hebrew-Codeswitching-Sentences Training dataset for English-Hebrew codeswitching sentences (training used for Parakeet + Nemo)
- model danielrosehill/Whisper-Hebrish Whisper fine tune trained on a small dataset of code switching sentences. POC demonstrated measurable improvements in code-switched vocabulary recognition.
- dataset danielrosehill/Read-Aloud-Voice-Sentences Voice audio dataset incorporating code switching sentences (English Hebrew) and tech "jargon"
- model danielrosehill/hebrew-latin-token-classifier
- space Hebrew-in-Latin Token Classifier
- space English-Hebrew Code-Switching Browser
- dataset Hebrish/English-Hebrew-Mixed-Sentences Older code-switching senence dataset
- space English-Hebrew Code-Switching ASR Leaderboard Leaderboard: stock vs fine-tuned ASR on English-Hebrew code-switching
- dataset Hebrish/English-Hebrew-Codeswitching-ASR-Benchmark Frozen benchmark test set (v1)
- model Hebrish/Whisper-Hebrish-Small-ACFT
- space Hebrish: try Sabich Try Sabich in your browser
- space Hebrish: try Jachnun Try Jachnun in your browser
Copied from Hugging Face on 7 November 2026.