Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
text-to-speech model
|
| gptkbp:application |
speech synthesis
|
| gptkbp:author |
Junho Kim, Jaehyeon Kim, Sungwon Kim, Bong-Jin Lee, Sungroh Yoon, and others
|
| gptkbp:basedOn |
gptkb:Variational_Inference
Transformer architecture |
| gptkbp:citation |
2021
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech |
| gptkbp:developedBy |
JUNNYU
|
| gptkbp:firstReleased |
2021
|
| https://www.w3.org/2000/01/rdf-schema#label |
Vits
|
| gptkbp:input |
gptkb:text
|
| gptkbp:notableFeature |
fast inference
voice cloning end-to-end TTS high-quality voice synthesis speaker adaptation |
| gptkbp:openSource |
true
|
| gptkbp:output |
audio
|
| gptkbp:relatedTo |
gptkb:Glow-TTS
gptkb:Tacotron gptkb:MelGAN FastSpeech |
| gptkbp:repository |
https://github.com/jaywalnut310/vits
|
| gptkbp:supportsLanguage |
multilingual
|
| gptkbp:usedFor |
voice conversion
singing voice synthesis |
| gptkbp:bfsParent |
gptkb:Hugging_Face_models
|
| gptkbp:bfsLayer |
7
|