Statements (25)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
speech synthesis model
|
| gptkbp:availableOn |
gptkb:Hugging_Face
|
| gptkbp:basedOn |
Transformer architecture
|
| gptkbp:citation |
100+
|
| gptkbp:developedBy |
gptkb:Microsoft_Research
|
| https://www.w3.org/2000/01/rdf-schema#label |
SpeechT5
|
| gptkbp:input |
gptkb:public_speaker
gptkb:text |
| gptkbp:language |
English
|
| gptkbp:memiliki_tugas |
text-to-speech
automatic speech recognition voice conversion speaker identification speech enhancement |
| gptkbp:notablePublication |
SpeechT5: Unified-Modal Encoder-Decoder Pre-training for Spoken Language Processing
|
| gptkbp:openSource |
yes
|
| gptkbp:output |
gptkb:public_speaker
gptkb:text |
| gptkbp:pretrained |
yes
|
| gptkbp:releaseYear |
2022
|
| gptkbp:url |
https://github.com/microsoft/SpeechT5
https://huggingface.co/microsoft/speecht5_tts |
| gptkbp:uses |
encoder-decoder architecture
|
| gptkbp:bfsParent |
gptkb:Hugging_Face_models
|
| gptkbp:bfsLayer |
7
|