Instructions to use Sharka/CIVQA_Impira_QA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Sharka/CIVQA_Impira_QA with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("document-question-answering", model="Sharka/CIVQA_Impira_QA")# Load model directly from transformers import AutoTokenizer, AutoModelForDocumentQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Sharka/CIVQA_Impira_QA") model = AutoModelForDocumentQuestionAnswering.from_pretrained("Sharka/CIVQA_Impira_QA") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
---
|
| 4 |
+
# Impira Document QA Model Fine-tuned with CIVQA dataset
|
| 5 |
+
|
| 6 |
+
This is a fine-tuned version of the [Impira model](https://huggingface.co/impira/layoutlm-document-qa), which was trained on Czech Invoice Visual Question Answering (CIVQA) datasets containing invoices in the Czech language.
|
| 7 |
+
|
| 8 |
+
This model enables Document Visual Question Answering on Czech invoices.
|
| 9 |
+
|
| 10 |
+
All invoices used in this dataset were obtained from public sources. Over these invoices, we were focusing on 15 different entities, which are crucial for processing the invoices.
|
| 11 |
+
- Invoice number
|
| 12 |
+
- Variable symbol
|
| 13 |
+
- Specific symbol
|
| 14 |
+
- Constant symbol
|
| 15 |
+
- Bank code
|
| 16 |
+
- Account number
|
| 17 |
+
- ICO
|
| 18 |
+
- Total amount
|
| 19 |
+
- Invoice date
|
| 20 |
+
- Due date
|
| 21 |
+
- Name of supplier
|
| 22 |
+
- IBAN
|
| 23 |
+
- DIC
|
| 24 |
+
- QR code
|
| 25 |
+
- Supplier's address
|