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
Automatic Speech Recognition • 0.6B • Updated • 3.31kNote Parakeet V2 fine-tuned for English/Hebrew code-switching
danielrosehill/English-Hebrew-Codeswitching-Sentences
Viewer • Updated • 5.47k • 1.07k • 1Note Training dataset for English-Hebrew codeswitching sentences (training used for Parakeet + Nemo)
danielrosehill/Whisper-Hebrish
Automatic Speech Recognition • 0.8B • Updated • 47Note Whisper fine tune trained on a small dataset of code switching sentences. POC demonstrated measurable improvements in code-switched vocabulary recognition.
danielrosehill/Read-Aloud-Voice-Sentences
Viewer • Updated • 12.4k • 2.4kNote Voice audio dataset incorporating code switching sentences (English Hebrew) and tech "jargon"
-
danielrosehill/hebrew-latin-token-classifier
Token Classification • 0.3B • Updated • 86 -
Hebrew-in-Latin Token Classifier
🔤Find romanized Hebrew words inside English text
-
English-Hebrew Code-Switching Browser
🎙Listen to English-Hebrew code-switching by term
Hebrish/English-Hebrew-Mixed-Sentences
Viewer • Updated • 637 • 110Note Older code-switching senence dataset
English-Hebrew Code-Switching ASR Leaderboard
🎙ASR on English speech with Hebrew words in it
Note Leaderboard: stock vs fine-tuned ASR on English-Hebrew code-switching
Hebrish/English-Hebrew-Codeswitching-ASR-Benchmark
Viewer • Updated • 324 • 181Note Frozen benchmark test set (v1)
-
Hebrish/Whisper-Hebrish-Small-ACFT
Automatic Speech Recognition • 0.2B • Updated • 32
Hebrish: try Sabich
🥙English dictation with Hebrew words, tech terms and numbers
Note Try Sabich in your browser
Hebrish: try Jachnun
🫓English dictation that gets the Hebrew words right
Note Try Jachnun in your browser