Hebrish
Technical

Models

Model inventory

All 17 models, by area: speech to text, text to speech and accessory models. Which are maintained, how often they are updated, what each is for and where it runs.

Which one should I use? Every model here can still be downloaded, and access requests for the older and less maintained ones are still approved. The up-to-date models (marked Recommended) are strongly recommended: they are the ones still being trained, so they recognise the widest vocabulary.

Recommended: maintained and updated. Available as is: downloadable, updated rarely or never. Legacy: replaced by a newer model. Separate project: listed for reference, not a Hebrish model. Latest versions of the models in the apps are read from the app download server when this page is built (2026-11-19).

Speech to text

Speech recognition (ASR): dictation, streaming and voice commands. All speech to text.

ModelStatusUse caseUpdatesPlatformsIn the Hebrish appsLatestLast releaseWeights
Jachnun
Code-switching only. Sabich covers the same words and more.
Available as is
Occasional updates
Use Sabich instead
Dictation (speech to text)Occasional updates, no scheduleBrowser, Linux, Windows, macOSNoJachnun v1.02026-10-19Hugging Face
Sabich-Canary-Qwen-2.5B
Sabich data on Canary-Qwen 2.5B, for desktop GPUs and servers.
Available as is
Frozen
Use Sabich instead
Dictation (speech to text)None plannedGPU serverNoSabich-Canary-Qwen-2.5B v1.02026-10-21Hugging Face
Sabich-Parakeet-110M
Small Sabich for low-end phones and wearables.
Available as is
Frozen
Use Sabich instead
Dictation (speech to text)None plannedAndroid, Low-power / wearablesNoSabich-Parakeet-110M v1.02026-10-21Hugging Face
Sabich-Qwen3-ASR-1.7B
One run comparing a Qwen3-ASR base with the Parakeet base.
Available as is
Proof of concept
Use Sabich instead
Dictation (speech to text)None: a one-off experimentGPU serverNoSabich-Qwen3-ASR-1.7B v1.02026-10-21Hugging Face
Sabich-asr4all
Smallest Sabich variants, streaming, for very low-power devices.
Available as is
Frozen
Use Sabich instead
Dictation (speech to text)None plannedLow-power / wearablesNoSabich-asr4all-S and -M v1.02026-10-21Hugging Face
Shakshuka
Streaming: words appear while you speak. The streaming choice in the desktop app (Android support not released yet). Sabich is the recommended model: more accurate, and Shakshuka is not recommended until its accuracy catches up.
Available as is
Occasional updates
Streaming dictationRetrained now and then while its accuracy is worked onLinux, WindowsDesktopShakshuka v2.22026-11-17Hugging Face
Whisper Hebrish
The first Hebrish model, on Whisper large-v3-turbo.
Legacy
Superseded
Use Sabich instead
Dictation (speech to text)NoneGPU serverNoVersion 22026-10-17Hugging Face
Whisper Hebrish Small ACFT
Early Whisper fine-tune for FUTO Keyboard.
Legacy
Superseded
Use Sabich instead
Dictation (speech to text)NoneAndroidNosmall-en-en30-acft2026-10-17Hugging Face

Text to speech

Speech synthesis (TTS). All text to speech.

ModelStatusUse caseUpdatesPlatformsIn the Hebrish appsLatestLast releaseWeights
Meorav-Daniel
Text-to-speech in Daniel's own voice.
Available as is
Frozen
Text to speechNone plannedGPU serverNoMeorav-Daniel v1.02026-11-15Hugging Face
Meorav-Multi-Voice
Five designed voices in one model.
Available as is
Frozen
Use Meorav instead
Text to speechNone plannedGPU serverNoMeorav-Multi-Voice v1.02026-11-16Hugging Face

Accessory models

Text tools that support the speech models. All accessory models.

ModelStatusUse caseUpdatesPlatformsIn the Hebrish appsLatestLast releaseWeights
Hebrew-Gendered-Sentence-Creator
Text tool: writes Hebrew sentences already gendered for the speaker, for Hebrew text-to-speech. Stage 1 of 2 (gender-aware nikud planned).
Available as is
Work in progress
Accessory (text tools)In developmentGPU serverNov3 (work in progress)2026-11-18Hugging Face
Hebrew-Latin Token Classifier
Text tool: finds romanized Hebrew words in English text, for text-to-speech.
Available as is
Frozen
Accessory (text tools)None plannedLinux, Windows, macOS, GPU serverNov12026-10-15Hugging Face

Machine-readable: /data/model-inventory.json. Help choosing a dictation model: Which model should I use?