Add support for TCN architectures as described in "User-Driven Fine-Tuning for Beat Tracking" by Pinto et al., 2021

[FabianB98]

This PR adds support for TCN architectures as described in the paper "User-Driven Fine-Tuning for Beat Tracking" by Pinto et al., 2021. Within this network architecture, the authors propose the usage of a TCN where each TCN layer uses two separate sets of dilated convolutions, where one of the dilated convolutions has a dilation of twice that of the first dilated convolution.

Implements the functionality suggested in issue #14.