README.md

MLo7_Diff-SVC_models

diff-svc models that are made/trained/owned by MLo7

Models info and permissions

---

Nehito Ketsu (24khz)

project_name: Nehito

tone: Male

step#: 1M

audio data: 6 hours | [4 hours of singing, 2 hours of raw concatenative synth samples]

VP: Ghin K.

Team Title: Archivoice

Permissions

render and share results: allowed

used for pretraining: allowed

NSFW: allowed

DEMO ___ (music by JVKE)

golden.hour.Diff-SVC.demo.render.mov

DOWNLOAD

---

Nehito Ketsu (44khz)

project_name: Nehito

tone: Male

step#: 1M

audio data: 8 hours | [6 hours of singing, 2 hours of raw concatenative synth samples]

VP: Ghin K.

Team Title: Archivoice

Permissions

render and share results: allowed

used for pretraining: allowed

NSFW: allowed

DEMO

##coming soon

This model was trained during the beta stage of 44khz diff-svc, so expect quality to differ

DOWNLOAD

---

Yokuatsu Takuto (24khz)

project_name: Takuto

tone: Male

step#: 250k | used pretrain

audio data: 2 hour, 18 minutes | [1 hour 22 minutes of raw concatenative synth samples + augmented pitch, 49 minutes of vsynth render]

VP: Taktger

Team Title: Taktger

Permissions

render and share results: allowed

used for pretraining: not allowed | due to this model was a ported model test

NSFW: allowed

DEMO ___ (music by VocaCircus)

DAWN_demo.mov

DOWNLOAD

---

Toshio Sasagawa (24khz)

project_name: Toshio

tone: Male

step#: TBD | used pretrain

audio data: 3 hour, 51 minutes | [3 hours 13 minutes of raw concatenative synth samples, 38 minutes of singing]

VP: Toshio Sasagawa

Team Title: Toshio

Permissions

render and share results: allowed

used for pretraining: not allowed | not enough singing data-type

NSFW: allowed

DEMO

##coming soon

DOWNLOAD COMING SOON