AWAS666

More UVR5 Models

1

It would be great to have a greater variety of UVR5 models. Especially the Kim Vocal ones are top notch in their own regard. Could someone please either add them...

Excel fails to open a generated file if you add cells in non linear order. For example: ``` var cells = new List(); cells.Add(new Cell(1, "Value1")); cells.Add(new Cell(3, "Value3")); cells.Add(new...

Using Pitch shift generates empty audio file

4

So I have been trying to use this to change the pitch of a tts voice on the fly. I basically just wanna apply the pitch shift to a wav...

[feature request] usable with the API endpoint of forge

2

Not sure if this already works, haven't found it at the very least. Would be cool to be able to use this with the API endpoint.

been experimenting on windows and this is basically what breaks it, not sure if just adding different encoding ruins it on other plattforms though... also the "train.sh" script doesn't work,...

[Question]: API docs?

8

### Describe your problem Couldn't find any swagger api on first glance to use this locally with an external code base and just as a RAG engine.

Kadinsky 2.1 could do any resolution, although some of them turned into rather bad responses. Kadinsky 2.2 seems to be fixed to certain ones. If I give it 1280x720 it...

Loud white noise on short texts with embedding_scale > 1

21

If I give it a short text like "Hello how are you?" it generates me a 25 second clip of extremly loud white noise. I tried this on the libritts...

WithNoSpeechThreshold doesn't seem to do anything

1

Either I lack the understanding what this is supposed to do or it doesn't work. I tried a variety values from 0.1f to 10f and I still had hallucinations remaining...

Garbage collector performance issue

7

Hey, using this in avalonia 11 and works pretty good out of the box, only minor issue I have that I do swap my bound image at like 30-60 fps...