Skip to content
Other

HeOCR R3h

распознавание строк на иврите

1 min read

R3h — модель распознавания текста для строк современных документов на иврите на базе kraken. Она читает печатные и «рукописные» строки, включая цифры, латиницу и типографскую пунктуацию. Это третий шаг пайплайна HeOCR: R4d находит строки, A1 задаёт порядок чтения, R3h распознаёт.

Ключевые особенности

  • Построена на стандартной recognition-сети ketos 7.0.2, line-level CTC.
  • Кодек на 117 символов: буквы иврита с конечными формами, geresh и gershayim, цифры, латиница, ASCII- и типографская пунктуация, знак шекеля.
  • Обучена с нуля только на синтетических страницах hocrsyngen; реальные сканы не использовались.
  • Ожидает baseline-сегментацию; лучше работает в связке R4d + A1 + R3h.
  • Это исследовательский baseline, а не production-транскрайбер.

Пример

pip install '.[kraken]'
heocr-engine kraken --api python --segmentation-model heocr-r4d-segmentation.safetensors --reading-order-model heocr-a1-reading-order.safetensors --reading-order-classes region --recognition-model heocr-r3h-recognition.safetensors page.jpg page.json
ПодробнееCER пайплайна: 0.020 на seed-101 и 0.010 на held-out; все оценки синтетические.
На CPU обработка одной страницы занимает около 8 секунд.
Ограничения: нет проверенной оценки на реальных сканах, niqqud и исторических рукописей; «handwriting-style» — один шрифт, а не реальный почерк.
Лицензия Apache-2.0.
Discuss Telegram 0

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # HeOCR/heocr-r3h-recognition
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download HeOCR/heocr-r3h-recognition --local-dir ~/models/heocr-r3h-recognition
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to heocr-r3h-recognition
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of heocr-r3h-recognition (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

HeOCR/heocr-r3h-recognition
Author
HeOCR
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments