Instructions to use purna419/invoice-parser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use purna419/invoice-parser with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="purna419/invoice-parser")# Load model directly from transformers import AutoTokenizer, AutoModelForImageTextToText tokenizer = AutoTokenizer.from_pretrained("purna419/invoice-parser") model = AutoModelForImageTextToText.from_pretrained("purna419/invoice-parser") - Notebooks
- Google Colab
- Kaggle
Awesome
#2
by fahmiaziz - opened
wowww!!! this model is really amazing, how did you achieve the model? are you fine tuning the donut base? coincidentally I am also making a model for invoice parsing.
Thanks! Yes this model is fine tuned over donut.
how to train it to get high accuracy, i have tried it and get 90% only. can you explain it?