AI & ML interests

Improving voice AI accuracy for code-switched English-Hebrew for English-speaking immigrants in Israel and the Jewish world. Models: ASR (focus), TTS ( POC / experimentary).

Recent Activity

danielrosehill  updated a model about 2 hours ago
Hebrish/Falafel-sherpa-onnx-int8
danielrosehill  updated a model about 2 hours ago
Hebrish/Falafel
View all activity

Organization Card

Hebrish היבריש: dictation that gets the Hebrew words right

Hebrish · היבריש

Dictation that gets the Hebrew words right.

Cartoon: at a makolet counter, a stock speech model pictures a French woman with a baguette; a speech bubble shows Micollette struck through and makolet written correctly

Ordinary dictation hears makolet and writes "Micollette". Hebrish writes the Hebrew word.

Hebrish builds open speech tools for code-switched English–Hebrew, for English-speaking immigrants in Israel and users throughout the Jewish world: speech recognition (ASR) that writes the Hebrew words correctly, and speech synthesis (TTS) that says them correctly. It is a one-person, not-for-profit project by Daniel Rosehill, and its models and data are open.

  • Models: see them all on one page in the Hebrish Models Space.
  • Speech recognition (ASR):
    • Sabich (Rolling), the default in the apps since 2026-11-02: Sabich trained further from its own weights on each new batch of recordings.
    • Sabich (Stable), the established release: code-switching plus tech vocabulary. Try either in your browser in the Sabich demo. The Sabich line comes in variants for every size of device: Qwen3-ASR-1.7B and Canary-Qwen-2.5B for desktop GPUs, Parakeet-110M for small devices, and asr4all-S and -M for wearables.
    • Jachnun: code-switching only.
    • Shakshuka: streaming, so the words appear while you speak.
    • Whisper Hebrish: Whisper fine-tunes, where the project started.
    • On-device builds (GGUF, ONNX, sherpa-onnx, MLX) are in -<format> repos. Which model should I use?
  • Speech synthesis (TTS):
    • Meorav: code-switching text-to-speech, a Qwen3-TTS fine-tune that reads code-switched English aloud and pronounces the Hebrew words in it correctly. Meorav PoC-1 is the first checkpoint: experimental, open (CC BY-NC 4.0), no benchmark yet. Training code: Meorav-TTS.
    • A token classifier that finds romanized Hebrew words in English text, for text-to-speech.
  • Data: read-aloud code-switching sentences and a frozen benchmark, scored by Hebrew-term recall on a clean subset. Also every Israeli street name (national list with English names from OpenStreetMap), the vocabulary source for street sentences. Results: hebrish.app/benchmarks.
  • Apps: Hebrish runs the models on-device on Android, Linux and Windows.

Everything in one place, including repos still on Daniel's personal account: the Hebrish collection.

Website: hebrish.app · GitHub: Hebrish-ASR