Skip to content
ModelListedExternal
Download

Crnn Fa License Plate Recognition v2

A robust CRNN-based OCR model for license plate recognition (Persian only)(V2). This model is a finetuned version of hezarai/crnn-fa-printed-96-long on the Persian license plate dataset (v1).

KindOtherBase modelhezarai/crnn-base-fa-v2VersionRevision 62db60d

Model source

Kind
Other
File size
35.5 MB
Base model
hezarai/crnn-base-fa-v2
Version
vRevision 62db60d
Updated
Sep 25, 2026
Downloads
4
Tasks
Captioning
Source
Hugging Face

Source description

A robust CRNN-based OCR model for license plate recognition (Persian only)(V2). This model is a finetuned version of hezarai/crnn-fa-printed-96-long on the Persian license plate dataset (v1).

Note that this model only works on a cropped image of a plate, so you have to run an object(license plate) detection model and pass its output to this model to work.

Usage

pip install hezar
from hezar.models import Model

model = Model.load("hezarai/crnn-fa-license-plate-recognition-v2")
plate_text = model.predict("assets/license_plate_ocr_example.jpg")
print(plate_text)  # Persian text of mixed numbers and characters might not show correctly in the console
['۵۷س۷۷۹۷۷']

Sources

1 source
Hugging FacePrimaryVersion 62db60d0dc5dfcae42a8871891fad2a150fa53c0
huggingface.co/keyanazz/crnn-fa-license-plate-recognition-v2/tree/62db60d0dc5dfcae42a8871891fad2a150fa53c0

Verified Sep 10

Model artifacts

1 artifact

model.pt

pt · 35.5 MB · SHA-256 c20ad7be2b1f…6620 · Hugging Face

Download file

Source excerpts

2 excerpts

--- language: - fa library_name: hezar tags: - image-to-text - hezar datasets: - hezarai/persian-license-plate-v1 pipeline_tag: image-to-text base_model: - hezarai/crnn-fa-printed-96-long --- A robust CRNN-based OCR model for license plate recognition (Persian only)(V2). This model is a finetuned version of [hezarai/crnn-fa-printed-96-long](https://huggingface.co/hezarai/crnn-fa-printed-96-long) on the [Persian license plate dataset (v1)](https://huggingface.co/datasets/hezarai/persian-license-plate-v1). Note that this model only works on a cropped image of a plate, so you have to run an object(license plate) detection model and pass its output to this model to work. ## Usage ``` pip install hezar ``` ```python from hezar.models import Model model = Model.load("hezarai/crnn-fa-license-plate-recognition-v2") plate_text = model.predict("assets/license_plate_ocr_example.jpg") print(plate_text) # Persian text of mixed numbers and characters might not show correctly in the console ``` ``` ['۵۷س۷۷۹۷۷'] ```

Source context: 4 downloads · 0 likes · Pipeline image-to-text · Library hezar · Repo keyanazz/crnn-fa-license-plate-recognition-v2