Stanisław Kacprzak

Removing of audio fetching from inference interface

5

The method `load_audio()` uses `fetch()` functionality, which (according to comments) is clearly intended to works with pretrained models, not audio files. This results in bloating working directory with symlinks to...

Refactoring of `forward()` method in `Discriminator`, to prevent last (unnecessary) downsampling. ```python def forward(self, x): results = [] for key, disc in self.model.items(): results.append(disc(x)) x = self.downsample(x) #

In a usage examples (README) `main.py` should be `runner.py`.

Error in TIMIT height conversion

1

It seems that due to missing `"` in the orginal TIMIT speaker info file, this repository contains [error in height conversion](https://github.com/shangeth/SpeakerProfiling/blob/7e5f3b013101fdc95732851e374f4170d2f97150/Dataset/data_info_height_age.csv#L422). Speaker `PAM1` is 5'11 which is 180.34, not 154.94....