Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- cs
|
| 5 |
+
tags:
|
| 6 |
+
- document question answering
|
| 7 |
---
|
| 8 |
+
# LayoutLMv2 Model Fine-tuned with CIVQA (Tesseract) dataset
|
| 9 |
+
|
| 10 |
+
This is a fine-tuned version of the [LayoutLMv2 model](https://huggingface.co/microsoft/layoutlmv2-base-uncased), which was trained on Czech Invoice Visual Question Answering (CIVQA) datasets containing invoices in the Czech language.
|
| 11 |
+
|
| 12 |
+
This model enables Document Visual Question Answering on Czech invoices.
|
| 13 |
+
|
| 14 |
+
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.
|
| 15 |
+
- Invoice number
|
| 16 |
+
- Variable symbol
|
| 17 |
+
- Specific symbol
|
| 18 |
+
- Constant symbol
|
| 19 |
+
- Bank code
|
| 20 |
+
- Account number
|
| 21 |
+
- ICO
|
| 22 |
+
- Total amount
|
| 23 |
+
- Invoice date
|
| 24 |
+
- Due date
|
| 25 |
+
- Name of supplier
|
| 26 |
+
- IBAN
|
| 27 |
+
- DIC
|
| 28 |
+
- QR code
|
| 29 |
+
- Supplier's address
|