How ready is multispeaker training?

p0p4k / pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper

https://neurips.cc/virtual/2023/poster/69899

MIT License

198 stars 28 forks source link

How ready is multispeaker training? #3

Closed kunibald413 closed 8 months ago

kunibald413 commented 8 months ago

found this TODO https://github.com/p0p4k/pflowtts_pytorch/blob/b00f7b45ad777c21fa42b77cd36df87e2ceeb9ef/pflow/data/text_mel_datamodule.py#L169

would like to try multispeaker training, it this good to have fixed for that or could i already give it a go?

p0p4k commented 8 months ago

The only small issue I need to fix is samples less than 3 seconds must be either discarded or use another sample as a prompt. I'll do it today or tomorrow.