Hebrish · היבריש

Dictation that gets the Hebrew words right.

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 personal project by Daniel Rosehill in Jerusalem.

New here? Start with the Hebrish Index: what Hebrish is and which model to use.

• Speech recognition (ASR), kept up to date:
  • Sabich Rolling: the one for most people. English with Hebrew words mixed in, plus tech vocabulary; retrained as new recordings come in, and what the Hebrish apps run.
  • Falafel: voice commands, the kind of thing you say to an AI agent or your computer.
  • Shakshuka: streaming, so the words appear while you speak.
  • For English without Hebrew, see Fritter, a separate project.
• Older models (no longer updated, kept for reference and citations; each card says so at the top): Sabich v1.0 to v2.4, Jachnun, the Sabich variants on other bases (Qwen3-ASR, Canary-Qwen, Parakeet 110M, asr4all) and Whisper Hebrish. All of them, with formats and results, in the Hebrish Models Space. Gated repositories approve requests automatically.
• 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. 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 · YouTube: Hebrish