fix: fix_loudness to -12 dB

[zgldh]

Fixed the loudness issue with the idea of https://github.com/myshell-ai/MeloTTS/issues/45#issuecomment-2092766621

Original output: https://zgldh.github.io/temp/original.wav

Fixed output: https://zgldh.github.io/temp/fixed_loudness.wav

[nwhitehead]

This is a good idea!

In the example output in the comment it seems to me like the audio is too loud everywhere. The waveform looks visually clipped and it sounds distorted. I think pyloudnorm is doing filtering to avoid clipping artifacts as much as it can but I still hear it.

I tried with other values and -18 seemed to be good. That sounded clean to me and matched the volume level of other spoken text sources.