Adaptation about mellotron HOT 5 OPEN

I assume you're training on a single speaker. Instead, train on all LibriTTS + your own data.

from mellotron.

I have a multi-speaker Data set (male and female both).
Total speaker = 21
The total size of data = 13.36 hours
Total audios ( audio length is between 3 to 10 seconds) = 14453

Each speaker has recorded around 40 minutes of audio.

I would like to train multi-speaker data using this repo.

1. should I train using existing LibriTTS pretrained weights?
2. or train on all LibriTTS + my data from scratch?

Any comments @rafaelvalle

from mellotron.

Hi @rafaelvalle could you please answer to the questions?

from mellotron.

@shwetagargade216 I would train with both if you are training with LibriTTS. You are going to train a multi-speaker setup anyway, so more data can only benefit in that case. If you have a different language, I would maybe try only your data. But these things you usually cannot know in advance. If you train with both, make sure the format is the same, i.e sampling frequency.

from mellotron.

@karkirowle From scratch training might be time-consuming and cost-effective, would like to try transfer learning first using libritts dataset.

And I do have an English language dataset.

from mellotron.