Add link to lilypond
Browse files
README.md
CHANGED
@@ -10,7 +10,7 @@ pipeline_tag: image-to-text
|
|
10 |
|
11 |
<!-- Provide a quick summary of what the model is/does. [Optional] -->
|
12 |
Image-To-Text model for optical music recognition.
|
13 |
-
The model is trained to predict simple notes in the
|
14 |
Training data consists of artificial, handwritten and white board images.
|
15 |
The model itself is based on [Donut](https://huggingface.co/docs/transformers/model_doc/donut).
|
16 |
|
|
|
10 |
|
11 |
<!-- Provide a quick summary of what the model is/does. [Optional] -->
|
12 |
Image-To-Text model for optical music recognition.
|
13 |
+
The model is trained to predict simple notes in the [LilyPond](https://en.wikipedia.org/wiki/LilyPond) format from a given image.
|
14 |
Training data consists of artificial, handwritten and white board images.
|
15 |
The model itself is based on [Donut](https://huggingface.co/docs/transformers/model_doc/donut).
|
16 |
|