Pretrained model for Multiple Speaker Embedding

Archives TTS (Text-to-Speech)
#1

Hi,

Looking at the benchmark notebook from the dev branch, there has been significant progress with GST’s. I was wondering if the results are good and would it be possible to share the pretrained model with mulitple speaker embeddings with the community for us explore?

Thanks

1 Like
#2

There is nothing fully functional yet. But will be released as soon as we have it.