Master Index

Hebrew AI Models

A catalog of AI models for the Hebrew language — LLMs, speech-to-text, text-to-speech, NLP, embeddings, translation, and more.

This is a community resource. Contributions welcome via pull request.

Last updated: April 1, 2026

Table of Contents

• Large Language Models (LLMs)

• Speech-to-Text / ASR

• Text-to-Speech (TTS)

• NLP Models

• Embeddings

• Translation

• Summarization

• OCR / Vision

• Speech Foundation Models

• Curated HF Collections

• Notable Projects & Resources

• Key Organizations

Large Language Models (LLMs)

dicta-il (Israel Center for Text Analysis)

• DictaLM-3.0-24B-Base — 24B · Base · Latest generation Hebrew LLM, large variant

• DictaLM-3.0-24B-Thinking — 24B · Reasoning · Thinking/reasoning variant

• DictaLM-3.0-Nemotron-12B-Base — 12B · Base · Nemotron-based Hebrew LLM

• DictaLM-3.0-Nemotron-12B-Instruct — 12B · Instruct · Instruction-tuned Nemotron

• DictaLM-3.0-1.7B-Base — 1.7B · Base · Compact Hebrew LLM

• DictaLM-3.0-1.7B-Instruct — 1.7B · Instruct · Instruction-tuned compact model

• DictaLM-3.0-1.7B-Thinking — 1.7B · Reasoning · Thinking variant of compact model

• dictalm2.0 — 7B · Base · Previous-gen Hebrew LLM (Mistral-based)

• dictalm2.0-instruct — 7B · Instruct · Instruction-tuned DictaLM 2.0

• BEREL_3.0 — Base · Biblical/Rabbinic Hebrew language model

• BEREL — Base · BERT for Early/Rabbinic Hebrew

yam-peleg

• Hebrew-Gemma-11B-V2 — 11B · Chat · Hebrew-adapted Gemma, v2

• Hebrew-Gemma-11B-Instruct — 11B · Instruct · Instruction-tuned Hebrew Gemma

• Hebrew-Gemma-11B — 11B · Base · Base Hebrew Gemma

• Hebrew-Mistral-7B — 7B · Base · Hebrew-adapted Mistral 7B

• Hebrew-Mistral-7B-200K — 7B · Base · Extended context (200K) Hebrew Mistral

Other Hebrew LLMs

• Hebrew_Nemo — SicariusSicariiStuff · 12B · Instruct · Hebrew fine-tune of Mistral Nemo

• Hebrew-GPT — XythicK · 1B · Instruct · Hebrew fine-tune of Llama 3.2 1B

• HebrewGPT-1B — Slasky · 1B · Base · Hebrew-native GPT trained from scratch

• HebrewGPT-296M — Slasky · 296M · Base · Smaller Hebrew-native GPT

• Hebrew-GPT2-345M-Stage — Norod78 · 345M · Base · Hebrew GPT-2

• hebrew-gpt_neo-small — Norod78 · ~125M · Base · Hebrew GPT-Neo small

• Llama-3.2-3B-Hebrew-Master — yonioz123 · 3B · Chat · Hebrew fine-tune of Llama 3.2

• hebrew-math-tutor-v1 — Intel · 4B · Instruct · Hebrew math tutoring model

• Hebrew-Mistral-7B-Instruct-v0.1 — ronmasas · 7B · Instruct · Hebrew instruction-tuned Mistral

• dictalm2.0-instruct-fine-tuned-alpaca-gpt4-hebrew — ronigold · 7B · Instruct · DictaLM 2.0 fine-tuned on Alpaca GPT-4 Hebrew

• SmolLM-135M-FakyPedia-EngHeb — Norod78 · 135M · Base · Bilingual English-Hebrew small LM

• gemma-3_4b_hebrew-lyrics-finetune — Norod78 · 4B · Fine-tune · Gemma 3 fine-tuned for Hebrew lyrics

Speech-to-Text / ASR

ivrit-ai

The leading Hebrew ASR project. Community-driven.

• whisper-large-v3-turbo-ct2 — Large · CTranslate2 · Top Hebrew ASR model, CT2 optimized (22K+ downloads)

• whisper-large-v3 — Large-v3 · Fine-tuned · Hebrew fine-tuned Whisper large-v3

• whisper-large-v3-turbo — Large-v3 · Fine-tuned · Hebrew fine-tuned Whisper turbo

• whisper-large-v3-ct2 — Large-v3 · CTranslate2 · CT2 format of Hebrew Whisper

• whisper-v2-d4 — Large-v2 · Fine-tuned · Earlier Hebrew Whisper fine-tune

• faster-whisper-v2-d4 — Large-v2 · Faster-Whisper · Faster-Whisper format

• pyannote-speaker-diarization-3.1 — Diarization · Hebrew speaker diarization

• pyannote-segmentation-3.0 — Segmentation · Hebrew audio segmentation

GitHub: ivrit-ai/ivrit.ai | ivrit-ai/asr-training

imvladikon

• wav2vec2-xls-r-300m-hebrew — 300M · ASR · Most downloaded Hebrew model (144K downloads)

• wav2vec2-large-xlsr-53-hebrew — 300M · ASR · Hebrew fine-tuned XLSR-53

• wav2vec2-xls-r-1b-hebrew — 1B · ASR · Hebrew fine-tuned XLS-R 1B

• wav2vec2-xls-r-300m-lm-hebrew — 300M · ASR+LM · With language model decoding

• whisper-medium-he — Medium · ASR · Hebrew Whisper medium

Other ASR

• whisper-heb-ipa — thewh1teagle · Hebrew Whisper with IPA phoneme output

• WhiStress — slprl · Hebrew stress/prosody-aware ASR

• hebrew_whisper — ShmuelRonen · Hebrew Whisper ASR project

  ShmuelRonen/hebrew_whisper View on GitHub

Text-to-Speech (TTS)

An emerging area for Hebrew — no production-grade standalone model yet, but active research.

• HebTTS — slp-rl (Technion) · Diacritic-free Hebrew TTS research

  slp-rl/HebTTS ★ 108

  The official implementation of "A Language Modeling Approach to Diacritic-Free Hebrew TTS"

  Python15 forksUpdated Jun 2025
  aihebrewslmstts

• SIMS-Llama3.2-3B — slprl · Speech-language model, 3B

• SIMS-7B — slprl · Larger speech-language model

• israwave — thewh1teagle · Hebrew TTS project

  thewh1teagle/israwave ★ 39

  Mission to create a Hebrew TTS model as powerful and user-friendly as WaveNet

  Python9 forksUpdated Jan 2025
  hebrewisraelpytorchtts

• Zonos-Hebrew — notmax123 · Hebrew variant of Zonos TTS

• hebrewTTS-orpheus3b — Trojanssafsdg · Hebrew Orpheus TTS 3B

• hebrew-orpheus-tts — rotem1121 · Hebrew Orpheus TTS variant

• phonikud — thewh1teagle · Hebrew diacritization/phonemization for TTS pipelines

• mms-tts-heb — thewh1teagle · Hebrew MMS TTS

NLP Models

BERT-based Foundation Models

• AlephBERT-base — onlplab (BIU) · Foundational Hebrew BERT (29.6K downloads)

• heBERT — avichr · Hebrew BERT

• Legal-heBERT — avichr · Hebrew BERT for legal domain

• DictaBERT — dicta-il · Hebrew BERT from Dicta

• DictaBERT-large — dicta-il · Large Hebrew BERT

• NeoDictaBERT — dicta-il · Next-gen DictaBERT

• NeoDictaBERT-bilingual — dicta-il · Bilingual Hebrew-English BERT

• AlephBertGimmel-base — dicta-il · Third-generation Hebrew BERT

• MsBERT — dicta-il · Hebrew BERT variant

• HeRo — HeNLP · Hebrew RoBERTa

• LongHeRo — HeNLP · Long-context Hebrew RoBERTa

Named Entity Recognition (NER)

• heBERT_NER — avichr · Hebrew NER (39K downloads)

• dictabert-large-ner — dicta-il · Large Hebrew NER

• dictabert-ner — dicta-il · Standard Hebrew NER

Sentiment Analysis

• heBERT_sentiment_analysis — avichr · Hebrew sentiment analysis

• dictabert-sentiment — dicta-il · Hebrew sentiment classifier

• hebEMO — avichr · Hebrew emotion detection (8 emotions: anger, fear, joy, surprise, sadness, disgust, anticipation, trust)

Morphology & Parsing

• dictabert-morph — dicta-il · Hebrew morphological analysis

• dictabert-joint — dicta-il · Joint morphological analysis

• dictabert-large-parse — dicta-il · Hebrew syntactic parsing

• dictabert-parse — dicta-il · Standard Hebrew parser

• dictabert-seg — dicta-il · Hebrew word segmentation

• dictabert-lex — dicta-il · Hebrew lexical analysis

• dictabert-syntax — dicta-il · Hebrew syntax analysis

Diacritization (Nikud)

• dictabert-large-char-menaked — dicta-il · Hebrew diacritization / nikud restoration (4.5K downloads)

• dictabert-char — dicta-il · Character-level Hebrew model

Other NLP

• hebrew_punctuation — Verbit · Punctuation · Hebrew punctuation restoration

• dictabert-heq — dicta-il · QA · Hebrew extractive question answering

• hebert_parashoot — imvladikon · QA · Hebrew reading comprehension

• hebrew-offensive-detection — KevynKrancenblum · Classification · Hebrew offensive language detection

• hebert-finetuned-hebrew-metaphor — tdklab · Classification · Hebrew metaphor detection

Embeddings

• neodictabert-bilingual-embed — dicta-il · Bilingual Hebrew-English embeddings

• sentence-transformers-alephbert — imvladikon · Hebrew sentence embeddings (4.9K downloads)

• sentence_transformers_alephbertgimmel_small — imvladikon · Smaller Hebrew sentence embeddings

Translation

• opus-mt-en-he — Helsinki-NLP · EN → HE · English to Hebrew translation

• opus-mt-tc-big-he-en — Helsinki-NLP · HE → EN · Hebrew to English, large model

• english-hebrew-translation — ashercn97 · EN ↔ HE · T5-based English-Hebrew translation

Summarization

• het5_summarization — imvladikon · Hebrew T5 for summarization

• het5_small_summarization — imvladikon · Smaller Hebrew T5 summarization

• cross_summarization_he_en — imvladikon · Cross-lingual Hebrew-English summarization

OCR / Vision

• testing-trOCR-hebrew-handwritten — sivan22 · TrOCR for Hebrew handwritten text

• paleo-hebrew-mt5-post-ocr-processing — mr3vial · Post-OCR correction for paleo-Hebrew

• paleo-hebrew-qwen3-vl-lora-post-ocr-processing — mr3vial · Vision-language post-OCR for paleo-Hebrew

Speech Foundation Models

• mhubert-base-25hz — slprl (Technion) · mHuBERT speech features at 25Hz

• slam / slam_scaled / slam_large — slprl · Speech-language alignment models

• StresSLM — slprl · Hebrew stress-aware speech-language model

• PAST — slprl · Prosody-aware speech model

Curated HF Collections

Curated Hugging Face collections (by danielrosehill) grouping Hebrew models, datasets, and spaces by task:

• Hebrew Large Language Models — LLMs with Hebrew capabilities

• Hebrew ASR — Hebrew automatic speech recognition models

• Whisper Hebrish — Whisper-based Hebrew/English models

• Hebrew TTS — Hebrew text-to-speech models

• English-Hebrew Translation — English ↔ Hebrew translation models

• Hebrew Punctuation Restoration — Models for restoring punctuation in Hebrew text

• Hebrew Diacritic Restoration — Models for restoring nikud/diacritics

• Hebrew Sentiment Classification Models — Sentiment classification

• Hebrew OCR Models — Hebrew OCR and vision models

• Hebrew Datasets — Datasets for Hebrew NLP/AI

• Hebrew AI Spaces — Hugging Face Spaces for Hebrew AI

Notable Projects & Resources

• NNLP-IL/Hebrew-Resources — Comprehensive list of Hebrew NLP resources

  NNLP-IL/Hebrew-Resources View on GitHub

• iddoberger/awesome-hebrew-nlp — Curated list of Hebrew NLP resources

  iddoberger/awesome-hebrew-nlp View on GitHub

• ivrit-ai/ivrit.ai — Main ivrit.ai codebase for Hebrew ASR

  ivrit-ai/ivrit.ai ★ 46

  ivrit.ai codebase

  Python14 forksUpdated Oct 2025

• ivrit-ai/asr-training — ASR training recipes for Hebrew

  ivrit-ai/asr-training View on GitHub

• ivrit-ai/eliezer — ivrit.ai's Hebrew bot

  ivrit-ai/eliezer View on GitHub

• slp-rl/HebTTS — Diacritic-free Hebrew TTS research

  slp-rl/HebTTS ★ 108

  The official implementation of "A Language Modeling Approach to Diacritic-Free Hebrew TTS"

  Python15 forksUpdated Jun 2025
  aihebrewslmstts

• thewh1teagle/israwave — Hebrew TTS project

  thewh1teagle/israwave ★ 39

  Mission to create a Hebrew TTS model as powerful and user-friendly as WaveNet

  Python9 forksUpdated Jan 2025
  hebrewisraelpytorchtts

• HebrewNLP/HebrewNLP4J — Java library for HebrewNLP API

  HebrewNLP/HebrewNLP4J View on GitHub

• danielrosehill/Hebrew-TTS-Providers — Directory of Hebrew TTS providers and services

  danielrosehill/Hebrew-TTS-Providers ★ 0

  Point in time snapshot of TTS providers with Modern Hebrew support

  Updated Mar 2026

• danielrosehill/Hebrew-Image-Generation-Eval — Evaluation of image generation models for Hebrew text

  danielrosehill/Hebrew-Image-Generation-Eval View on GitHub

• danielrosehill/Hebrew-LLMs — Resource list of Hebrew large language models

  danielrosehill/Hebrew-LLMs View on GitHub

• AvrahamRaviv/Deep-Learning-in-Hebrew — Deep learning educational resources in Hebrew

  AvrahamRaviv/Deep-Learning-in-Hebrew View on GitHub

• ShmuelRonen/hebrew_whisper — Hebrew Whisper ASR project

  ShmuelRonen/hebrew_whisper View on GitHub

Key Organizations

• dicta-il — LLMs, BERT, NLP · Israel Center for Text Analysis. Most comprehensive Hebrew NLP toolkit

• ivrit-ai — ASR / STT · Leading Hebrew speech recognition project. Community-driven. Website: ivrit.ai

• yam-peleg — LLMs · Hebrew Gemma and Mistral adaptations

• avichr — NLP · heBERT family — widely used Hebrew NER and sentiment

• onlplab — Foundation BERT · AlephBERT — foundational Hebrew BERT from Bar-Ilan University

• imvladikon — ASR, embeddings · wav2vec2 Hebrew (144K downloads), sentence transformers

• slprl — TTS, speech · Technion Speech Processing Lab

• HeNLP — Foundation models · HeRo (Hebrew RoBERTa)

• Helsinki-NLP — Translation · OPUS-MT Hebrew translation models

• Norod78 — Small LLMs · Hebrew GPT-2, GPT-Neo, creative fine-tunes

• Slasky — LLMs · Hebrew-native GPTs trained from scratch

• thewh1teagle — TTS, phonemization · israwave TTS, phonikud diacritization

• Intel — Education LLMs · Hebrew math tutoring model

Contributing

Know of a Hebrew AI model not listed here? Open a pull request or file an issue.

License

creativecommons.org

Deed - Attribution 4.0 International - Creative Commons

This work is licensed under a Creative Commons Attribution 4.0 International License.