This repository contains the source code for the paper with the same title. Please note that the model presented here is currently configured just for the iKala dataset, as published in the corresponding paper. We will release a more generalized model soon.
To install, clone the repository and usepip install requirements.txt
The main code is in the train_tf.py file. To use the file, you will have to download the model weights and place it in the log_dir_m1 directory, defined in config.py. Wave files to be tested should be placed in the wav_dir, as defined in config.py. You will also require TensorFlow to be installed on the machine.
Once the iKala files have been put in the wav_dir, you can run
python prep_data_ikala.py
Once setup, you can run the command
python train_tf.py -t
python train_tf.py -s <filename> -p (optional, for plots)
Once the file has been synthesized, you can add examples to be evaluated to the sep_eval folder. Then to evaluate, please run
python sep_eval.py
We are currently working on future applications for the methodology and the rest of the files in the repository are for this purpose, please ignore. We will further update the repository in the coming months.
The TITANX used for this research was donated by the NVIDIA Corporation. This work is partially supported by the Towards Richer Online Music Public-domain Archives (TROMPA) project.