---
title: README
emoji: 🗣️
colorFrom: green
colorTo: yellow
sdk: static
pinned: false
---

![Hebrish עבריש: dictation that gets the Hebrew words right](https://huggingface.co/spaces/Hebrish/README/resolve/main/banner.png)

# Hebrish · עבריש

**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](https://cdn.hebrish.app/img/illustrations/gag-makolet.webp)

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

Hebrish improves ASR accuracy for code-switched English–Hebrew, for English-speaking immigrants in Israel and users throughout the Jewish world. 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](https://huggingface.co/spaces/Hebrish/Hebrish-Models).
  - [Sabich](https://huggingface.co/Hebrish/Sabich), recommended in the apps: code-switching plus tech vocabulary. It comes in variants for every size of device: [Qwen3-ASR-1.7B](https://huggingface.co/Hebrish/Sabich-Qwen3-ASR-1.7B) and [Canary-Qwen-2.5B](https://huggingface.co/Hebrish/Sabich-Canary-Qwen-2.5B) for desktop GPUs, [Parakeet-110M](https://huggingface.co/Hebrish/Sabich-Parakeet-110M) for small devices, and [asr4all-S](https://huggingface.co/Hebrish/Sabich-asr4all-S) and [-M](https://huggingface.co/Hebrish/Sabich-asr4all-M) for wearables.
  - [Jachnun](https://huggingface.co/Hebrish/Jachnun): code-switching only.
  - [Shakshuka](https://huggingface.co/Hebrish/Shakshuka): streaming, so the words appear while you speak.
  - Whisper Hebrish, and a [token classifier](https://huggingface.co/Hebrish/Hebrew-Latin-Token-Classifier) for romanized Hebrew.
  - On-device builds (GGUF, ONNX, sherpa-onnx, MLX) are in `-<format>` repos. [Which model should I use?](https://hebrish.app/models/choose)
- **Data:** read-aloud code-switching sentences and a frozen benchmark, scored by Hebrew-term recall on a clean subset. Results: [hebrish.app/benchmarks](https://hebrish.app/benchmarks).
- **Apps:** [Hebrish](https://github.com/Hebrish-ASR/Hebrish-App) 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](https://huggingface.co/collections/Hebrish/hebrish-english-hebrew-code-switching-6ad6143c7de198780425709f).

Website: [hebrish.app](https://hebrish.app) · GitHub: [Hebrish-ASR](https://github.com/Hebrish-ASR)