Skip to content
Other

PP-OCRv6 Tiny Cyrillic

быстрый OCR для кириллицы

1 min readupdated

PP-OCRv6 Tiny Cyrillic — компактная модель распознавания текста от Metrika Labs на базе PP-OCRv6. Это tiny-вариант для печатного и рукописного текста на кириллице, совместимый с PaddleOCR; для CPU есть ONNX/RapidOCR-версия.

Ключевые особенности

  • Поддерживает русский и другие кириллические языки: казахский, белорусский, узбекский, таджикский, украинский, болгарский, сербский, татарский, киргизский, монгольский и др.
  • Рукописный текст пока только на русском: чёткий почерк читает хорошо, с курсивом возможны ошибки.
  • Работает через PaddleOCR; для быстрого CPU-инференса есть ONNX-вариант и RapidOCR.
  • Обучена на 7,5 млн примеров сканов и синтетики; 80% — русский, 20% — другие языки с кириллицей.

Пример

from huggingface_hub import snapshot_download
from paddleocr import PaddleOCR
model_dir = snapshot_download("metrika-labs/PP-OCRv6_tiny_rec_cyrillic_safetensors")
ocr = PaddleOCR(text_recognition_model_name="PP-OCRv6_tiny_rec", text_recognition_model_dir=model_dir, text_detection_model_name="PP-OCRv6_small_det", engine="transformers")
results = ocr.predict("document.jpg")
ПодробнееВ примере карточки Tiny распознала фразу «Мир меняется быстро» как «Пир меняется быстро» (score 0.8412), Medium — верно (0.9882).
Для handwritten-текста поддержка ограничена русским; курсив и неразборчивый почерк могут давать ошибки.
Требования к VRAM/железу в карточке не указаны.
Примеры
Discuss Telegram 0 8

Will it run?

Runs in F32

Fits without quantisation.

  • F32weights 0.0 GB · ready files0.5 GB
  • BF16weights 0.0 GB0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · F32 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

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.

    # metrika-labs/PP-OCRv6_tiny_rec_cyrillic_safetensors
    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 metrika-labs/PP-OCRv6_tiny_rec_cyrillic_safetensors --local-dir ~/models/PP-OCRv6_tiny_rec_cyrillic_safetensors
    # The model is in ~/models. How to run it is in the model card (link above).
  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 PP-OCRv6_tiny_rec (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 1All on Hugging Face
Fine-tunes 2All on Hugging Face

About the model

metrika-labs/PP-OCRv6_tiny_rec_cyrillic_safetensors
Author
metrika-labs
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

80

Ask AI about this model

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

Comments

Computer vision

Aurum 4B

Aurum 4B