This is the code and the dataset for the paper titled
accepted at The 26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD’22), May 16-19, 2022, Chengdu, China.
If you end up using this code or the data, please cite our paper. (Citation coming soon!)
The dataset has been uploaded at the following Google Drive link - here
After downloading this version of the dataset, extract it.
Run the model.py as follows -
python model.py
This will pickle models for for transcription and also print performance metrics. To run the version of the model without the onset predictions, use model_without_onsets.py.
If you face any problem in running this code, you can contact us at meet20012[at]iiitd[dot]ac[dot]in or priya20033[at]iiitd[dot]ac[dot]in or brihi16142[at]iiitd[dot]ac[dot]in
Copyright (c) 2022 Priya Mehta, Meet Maheshwari, Brihi Joshi, Tanmoy Chakraborty
For license information, see LICENSE or http://mit-license.org