Ruta explaining xVAPitch
Browse files
README.md
CHANGED
@@ -39,7 +39,9 @@ pipeline_tag: text-to-speech
|
|
39 |
|
40 |
GitHub project: https://github.com/DanRuta/xVA-Synth
|
41 |
|
42 |
-
The base model for training other xVASynth's "xVAPitch" type models (v3). Model itself used by the xVATrainer TTS model training app. All created by Dan Ruta.
|
|
|
|
|
43 |
|
44 |
When used in xVASynth editor, it is an American Adult Male voice. Default pacing is too fast and has to be adjusted.
|
45 |
|
|
|
39 |
|
40 |
GitHub project: https://github.com/DanRuta/xVA-Synth
|
41 |
|
42 |
+
The base model for training other xVASynth's "xVAPitch" type models (v3). Model itself is used by the xVATrainer TTS model training app and not for inference. All created by Dan Ruta.
|
43 |
+
|
44 |
+
`The v3 model now uses a slightly custom tweaked VITS/YourTTS model. Tweaks including larger capacity, bigger lang embedding, custom symbol set (a custom spec of ARPAbet with some more phonemes to cover other languages), and I guess a different training script.` - Dan Ruta
|
45 |
|
46 |
When used in xVASynth editor, it is an American Adult Male voice. Default pacing is too fast and has to be adjusted.
|
47 |
|