AWAS666
AWAS666
I'm having the same problem. The issue seems to be that the image file doesn't get copied int the ebook file.  It only creates a file without extension which...
I did just use the the tutorial and switch it up with pitchshift ``` board = Pedalboard([PitchShift(semitones=7.0)]) # Open an audio file for reading, just like a regular file: with...
Nvm also seems to happen on single words, setting both alpha and beta to zero makes it return to normal though.
Windows 10 Python 3.11.4 Torch 2.1.0+cu118 _And loading the model to the GPU instead of CPU, but I'll do some further testing to narrow it down_ This doesn't seem to...
> Could you make a conda environment with Python 3.10 instead? You can run the colab demo and check package versions there and make sure you install these packages instead....
Tried it in collab aswell, if I put in just the word "wink" as inference text, it will give me bad white noise.
Is there a way around it without retraining it, like dropping the diffusion model on short inputs? Otherwise that likely means having to retrain, right?
not a pretty solution either :) but at least it isnt my setup alone
> @AWAS666 It still works even with a single word `wink.`. It did generate noise if there is no punctuation after this. I think this is caused by the training...
Great to hear