StyleTTS2 using Mimic-3 styles
#2
by
dkounadis
- opened
Audio styles & StyleTTS2 output for the Experiments of ArXiv - script Mimic-3 / script - pre-gen
|
|
|
|
Mimic-3 English Mimic-3 English - (Harvard) |
StyleTTS - (Mimic-3 English) |
|
Mimic-3 English 4x Mimic-3 En. 4x - (Harvard) |
StyleTTS2 - (Mimic-3 English 4x) |
|
Human - (EmoDB) Human - (LibriSpeech) |
StyleTTS2 - (EmoDB) StyleTTS2 - (LibriSpeech) |
|
Mimic-3 Foreign Mimic-3 Foreign - (Harvard) |
StyleTTS2 - (Mimic-3 Foreign) |
|
Mimix-3 Foreign 4x Mimic-3 Foreign 4x - (Harvard) |
StyleTTS2 - (Mimic-3 Foreign 4x) |
dkounadis
changed discussion title from
Mimic-3 style / StyleTTS2 output
to StyleTTS2 using Mimic-3 styles
dkounadis
changed discussion title from
StyleTTS2 using Mimic-3 styles
to StyleTTS2 via Mimic-3 styles
dkounadis
changed discussion title from
StyleTTS2 via Mimic-3 styles
to StyleTTS2 driven by Mimic-3 style
dkounadis
changed discussion title from
StyleTTS2 driven by Mimic-3 style
to StyleTTS2 driven by Mimic-3 styles
dkounadis
changed discussion title from
StyleTTS2 driven by Mimic-3 styles
to StyleTTS2 using Mimic-3 styles