donut · Issues· 211 open

app.py Failing for Python 3.9

Colab Demo CORD (Document Parsing) is Broken

Model inferencing from the saved files generated by train.py

Issue encountered while training the cord-v2

Tree Edit Distance (TED) based accuracy score: 0.0, F1 accuracy score: 0.0 on test data

How many documents(invoices) are required for training model for document information extraction?

Got wrong inference result

Questions about SynthDoG synthetic data

Reading order for pseudo-OCR pre-training task

dataset

Provide a working list of deps

Donut generate ONLY <s><s>...<s></s>

why get the result like this

ground_truth = json.loads(sample["ground_truth"]) KeyError: 'ground_truth'

Training doesn't start