Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
drbaph
/
MegaTTS3-WaveVAE
like
5
Text-to-Speech
Transformers
Safetensors
PyTorch
tts
voice-cloning
speech-synthesis
audio
chinese
english
zero-shot
diffusion
arxiv:
2502.18924
arxiv:
2408.16532
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
MegaTTS3-WaveVAE
/
g2p
/
generation_config.json
drbaph
Upload 24 files
4bd73f1
verified
7 months ago
raw
Copy download link
history
blame
contribute
delete
117 Bytes
{
"bos_token_id"
:
151643
,
"eos_token_id"
:
151643
,
"max_new_tokens"
:
2048
,
"transformers_version"
:
"4.48.3"
}