TrOCR Vietnamese Handwriting

This model is a fine-tuned version of microsoft/trocr-large-handwritten
on a Vietnamese handwriting dataset.

Results

  • eval_loss: 5.02
  • eval_runtime: 113.95
  • eval_samples_per_second: 10.76
  • eval_steps_per_second: 2.69

Model description

VisionEncoderDecoder (ViT + TrOCR) model trained for Vietnamese OCR.

Downloads last month
19
Safetensors
Model size
0.5B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Evaluation results