A TrOCR model for Persian. This is just a preview to verify the model works in Hezar. This model will be trained on more and better datasets soon!

Example

from hezar.models import Model

model = Model.load("trocr-base-fa-v1")
text = model.predict(["image.jpg"])
print(text)

Downloads last month: 14

Inference Providers NEW

Image-to-Text

This model is not currently available via any of the supported third-party Inference Providers, and the HF Inference API does not support hezar models with pipeline type image-to-text