search

p0p4k / pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper
https://neurips.cc/virtual/2023/poster/69899
MIT License
214 stars 30 forks source link

Unused model #23

Closed Tera2Space closed 8 months ago

Tera2Space commented 8 months ago

In speech_prompt_encoder we define speech_prompt_encoder but it's usage is commented So model is unused or used in different place?

p0p4k commented 8 months ago

There are two ways to project the speech prompt to desired channels. I am using one and commenting the other. Either can be used.

Tera2Space commented 8 months ago

I mean that the model creation is not commented but then model is not called anywhere, in this case it just takes up space.

p0p4k commented 8 months ago

I see, good catch. Can be commented out if not used.