vits · Issues· 165 open

Documentation Enhancement Suggestion

Question on the design choice of volume-preserving flow in the prior encoder

Need Piple onnx file for URDU language

VITS codes failed to run for Python 3.10.12

how many steps do we need in LJSPeech

Inference result is not as good as the demo

VITS fails to synthesize intelligible audio from Punjabi dataset using CISAMPA phoneme input

Cannot create core.cpython-310-x86_64-linux-gnu.so file when try to run python setup.py build_ext --inplace

Problems adding a new speaker

Questions about 48k audio file train

When I run train_ms.py on WSL2 get CUDA error and something.

when training this model by the our custom datasets we are facing the below error constantly "Dimension out of range (expected to be in range of [-1, 0], but got 1)"

Parenthases (and some other characters) lead to keyerror on inference

Code doesn;t even run. so many errors intalling pip

Not all .wav files generate corresponding spec.pt