Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,13 @@ metrics:
|
|
| 3 |
- accuracy
|
| 4 |
- roc_auc
|
| 5 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
More details in https://www.kaggle.com/code/dima806/speech-accent-multiclass-classification.
|
|
|
|
| 3 |
- accuracy
|
| 4 |
- roc_auc
|
| 5 |
---
|
| 6 |
+
Currently, the model returns the confidence score that the input audio is created by one of the following classical composers
|
| 7 |
+
found in [MusicNet Dataset](https://www.kaggle.com/datasets/imsparsh/musicnet-dataset) - a curated collection of 330 freely-licensed
|
| 8 |
+
labeled classical music recordings - used for the training of this model:
|
| 9 |
+
- [Beethoven](https://en.wikipedia.org/wiki/Ludwig_van_Beethoven);
|
| 10 |
+
- [Bach](https://en.wikipedia.org/wiki/Johann_Sebastian_Bach);
|
| 11 |
+
- [Schubert](https://en.wikipedia.org/wiki/Franz_Schubert);
|
| 12 |
+
- [Mozart](https://en.wikipedia.org/wiki/Wolfgang_Amadeus_Mozart);
|
| 13 |
+
- [Brahms](https://en.wikipedia.org/wiki/Johannes_Brahms).
|
| 14 |
+
|
| 15 |
More details in https://www.kaggle.com/code/dima806/speech-accent-multiclass-classification.
|