Benchmark RTF for all method: Melgan - MBMelgan - Hifigan - StyleGAN

[v-nhandt21]

I have 3 questions to confirm my experiment on these vocoder models:

1: Are there anyone have a comparing summaries between all model in RTF (with light and heavy version) ?

2: One more thing is that should we train a multiband hifigan to improve performance of Hifigan (Using stft loss)

3: What is the quality of voice produced by melgan and multiband-melgan, which is better?

[OnceJune]

Here's an RTF summary: https://github.com/xcmyz/FastVocoder#rtf