k2kobayashi/crank
A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder
PythonMIT
Issues
- 3
- 4
- 0
- 0
How to convert new audio files after all stages are complete and model is trained?
#58 opened by talka1 - 0
support for directml
#55 opened by talka1 - 0
KeyError: 'use_raw' Error at Stage 3
#56 opened by talka1 - 0
Stage 3 to stage 5 only Gpu...
#54 opened by talka1 - 0
failing at Stage 1
#53 opened by talka1 - 0
Stage 2 breaks at bad quality voice.
#50 opened by Vadim2S - 0
print() sometimes missing in log
#49 opened by Vadim2S - 4
- 8
KeyError "mcep"
#43 opened by misbullah - 0
ValueError: numpy.ndarray size changed
#46 opened by 980202006 - 4
ValueError: too many values to unpack (expected 3)
#41 opened by talka1 - 1
- 6
Output audio is shorter than input audio
#31 opened by DareenHarthi - 2
A copy of your paper
#39 opened by ThyrixYang - 1
runtime error
#34 opened by pavelxx1 - 2
Poor conversion quality. What am I doing wrong?
#27 opened by pavelxx1 - 1
Windows Support
#19 opened by hellc - 3
Dataset question
#25 opened by pavelxx1 - 1
KeyError: 'speaker_adversarial'
#26 opened by pavelxx1 - 1
Upload conversion samples
#14 opened by k2kobayashi - 3
Feature
#8 opened by k2kobayashi - 0
Models to be implemented
#13 opened by unilight - 2
Waveform load/write module
#9 opened by unilight - 1
- 6
Neural vocoder support
#2 opened by unilight