Michael Hansen
Michael Hansen
Yes, I've trained several voices from that dataset. Unfortunately, they perform very poorly on short sentences because the dataset comes from audio books (where short sentences are less common). Most...
Very odd, I can confirm this is a problem with the medium/high quality Ryan voices. The low quality voice seems to work, though. My only guess is that (1) there...
There are two ways of doing this that I know about, but only one that I've tried. The first way is training a "multi-speaker" model where each "speaker" is an...
I don't have a dataset where the audio from Mary Ann is split out by emotion.
What version of PyTorch did you use to export the onnx model?
Punctuation is stripped before matching now in hassil 2.0, so this should be fixed.
@alexkramer98 Thanks for the improvements! What do you think of the feedback?
I don't have a strong reason for it. I haven't experimented much with different ways of padding (except removing the padding, which seemed to make things worse). Basically, I went...
What CPU is it running on?
What VoIP hardware are you using? I'm using the Grandstream HT802 and am not seeing any problems.