Update README.md
Browse files
README.md
CHANGED
@@ -1,30 +1,8 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
language:
|
4 |
-
- en
|
5 |
-
pipeline_tag: image-to-text
|
6 |
-
datasets:
|
7 |
-
- katanaml-org/invoices-donut-data-v1
|
8 |
-
---
|
9 |
-
|
10 |
-
## Sparrow - Data extraction from documents with ML
|
11 |
-
|
12 |
-
This model is finetuned Donut ML base model on invoices data. Model aims to verify how well Donut performs on enterprise docs.
|
13 |
-
|
14 |
-
Mean accuracy on test set: 0.96
|
15 |
-
|
16 |
-
Inference:
|
17 |
-
|
18 |
-
![Inference Results](https://raw.githubusercontent.com/katanaml/sparrow/main/sparrow-ui/assets/inference_actual.png)
|
19 |
-
|
20 |
-
Training loss:
|
21 |
-
|
22 |
-
![Training Loss](https://raw.githubusercontent.com/katanaml/sparrow/main/sparrow-ui/assets/donut_training_loss.png)
|
23 |
-
|
24 |
-
Sparrow on [GitHub](https://github.com/katanaml/sparrow)
|
25 |
-
|
26 |
-
Sample invoice [docs](https://github.com/katanaml/sparrow/tree/main/sparrow-ui/docs/images) to use for inference (docs up to 500 were used for fine-tuning, use docs from 500 for inference)
|
27 |
-
|
28 |
-
Our website [KatanaML](https://www.katanaml.io)
|
29 |
-
|
30 |
-
On [Twitter](https://twitter.com/katana_ml)
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
pipeline_tag: image-to-text
|
6 |
+
datasets:
|
7 |
+
- katanaml-org/invoices-donut-data-v1
|
8 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|