This model is finetuned Donut ML base model on invoices data. Model aims to verify how well Donut performs on enterprise docs.
Mean accuracy on test set: 0.96
Inference:

Training loss:

Sparrow on GitHub
Sample invoice docs to use for inference (docs up to 500 were used for fine-tuning, use docs from 500 for inference)
Our website KatanaML
On Twitter