liusongxiang/StarGAN-Voice-Conversion
This is a pytorch implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
Python
Issues
- 1
D/loss_real: -0.0000
#21 opened by lihao612 - 0
Error in training with more than 4 speakers
#20 opened by sainishalini - 0
How to fine-tune StarGAN-VC model?
#19 opened by hongchengzhu - 0
not find gated cnn
#18 opened by dyyzhmm - 0
Why g_loss is lack of g_loss_identity
#17 opened by ywh-my - 7
model is not stargan-vc
#2 opened by hujinsen - 0
- 24
I cannot run the code.
#10 opened by Husnain08 - 0
Suggestions for documentation
#15 opened by karkirowle - 4
preprocessing.py possible sox issue
#12 opened by SamuelBroughton - 4
Loss function meanings
#14 opened by AlexMessner - 5
Can implementation of the author share 200000 iteration model for comparative study?
#4 opened by leokwu - 3
Inference time
#3 opened by carlfm01 - 1
Id mapping loss
#13 opened by SamuelBroughton - 2
How should I take it?Thank you!
#9 opened by apple12358lp - 0
- 2
- 1
run Convert.py wrong
#8 opened by DYJ1111 - 0
A question about the adversarial loss.
#5 opened by lhppom - 1
Python 3.5
#7 opened by sniperwrb - 1
About how to run this repo
#1 opened by MorganCZY