NVIDIA / mellotron

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data
BSD 3-Clause "New" or "Revised" License
854 stars 184 forks source link

how to train? #113

Open loboere opened 2 years ago

loboere commented 2 years ago

Can you tell me how to train this. does it train in the same way as tacotron 2?