sidharthrajaram/StyleTTS2
🐍 🤖 Pip installable package for StyleTTS 2 human-level text-to-speech and voice cloning
PythonNOASSERTION
Issues
- 1
Getting random pauses
#21 opened by samyoed - 1
add speed option to inference
#6 opened by mrciolino - 1
- 1
New realease 0.1.7
#22 opened by ManueleNolli - 4
Strange dependencies?
#16 opened by flatsiedatsie - 3
Use Tortoise splitter
#11 opened by fakerybakery - 1
torch version specifity
#17 opened by rsxdalv - 2
Return value as byte stream
#19 opened by ManueleNolli - 4
LJSpeech Model
#2 opened by fakerybakery - 1
Are there any known issues of this running on GPU instead of CPU? or at least can this run on GPU? or is there a option to make it run on GPU?
#15 opened by DrewThomasson - 3
Some text inputs throw expanded size of the tensor
#14 opened by Cabeda - 0
more so feature request- Add a loading bar for when you give it a very large chunk of text
#10 opened by DrewThomasson - 1
the text cleaner appears to strip valid numbers
#13 opened by thetrebor - 1
DeepPhonemizer
#9 opened by fakerybakery - 2
option to save models to local folder
#7 opened by mrciolino - 4
issue with phoneme.py that I fixed?
#5 opened by DrewThomasson - 2
Pass Style Directly
#3 opened by fakerybakery - 2
Allow direct output from inference
#1 opened by fakerybakery