profile
viewpoint

CorentinJ/Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

https://github.com/CorentinJ/Real-Time-Voice-Cloning

CorentinJ

viewpoint

Express your opinions freely and help others including your future self

Issues rank

demo_cly.py : TypeError("argument of type 'WindowsPath' is not iterable") hot 36
Import Error:(Failed to import any qt binding) hot 33
ValueError: frames must be specified for non-seekable files hot 19
google colab hot 17
demo_cly.py : TypeError("argument of type 'WindowsPath' is not iterable") hot 15
is there a way to configure it so that, rather than differentiate voices by speakers, it creates a composite voice trained on a few different speakers? hot 12
PyTorch installation is not configured to use CUDA hot 9
getting massive error when getting webrtcvad hot 8
No such file or directory: 'encoder\\saved_models\\pretrained.pt' hot 7
ERROR: Could not find a version that satisfies the requirement tensorflow-gpu hot 7
"Caught exception: PortAudioError('Error querying device -1')" error hot 7
error: command 'cl.exe' failed: No such file or directory hot 6
ModuleNotFoundError: No module named 'synthesizer.tacotron2' hot 6
AttributeError: module 'numba' has no attribute 'jit' - Real-Time-Voice-Cloning hot 1
Unable to unzip VoxCeleb1 and VoxCeleb2 - Real-Time-Voice-Cloning hot 1

contributors (According to the first 100)

CorentinJ
blue-fish
alexpeattie
matheusfillipe
vanpelt
lidalei
Jackson-Kang
mathigatti
Niwala
cforcomputer
ramalamadingdong
rancoud
ak9250
cclauss