Text-to-Speech
Safetensors
English
Chinese

the .npy latent file

#3
by yuanjv - opened

The UI require the .npy latent file where can I get it?

ByteDance org

@yuanjv Please follow the instruction in the model card to get .npy latent file. Sincerely thanks for your attention.

@yuanjv The model documentation states: For security issues, we do not upload the parameters of WaveVAE encoder to the above links. You can only use the pre-extracted latents from link1 for inference.
This means that we currently cannot obtain the custom audio voiceprint npy files, possibly due to copyright protection or to prevent misuse. However, the model architecture is quite informative and performs well, at least for Chinese TTS task.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment