issues
search
yl4579
/
StarGANv2-VC
StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
MIT License
466
stars
110
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Questions about Style diversification loss
#50
Chevalier1024
closed
2 years ago
1
What is the Overall Compute Footprint of the Pipeline?
#49
snakers4
closed
2 years ago
2
How to improve multilingual singing voice conversion?
#48
MMMMichaelzhang
closed
2 years ago
9
Latent representation
#47
meyerdav
closed
2 years ago
2
Update style encoder after deleting mapping network
#46
Charlottecuc
closed
2 years ago
2
how to infer with my own audio files
#45
mehmetariftasli
closed
2 years ago
1
A problem about Log norm loss
#44
vanetspark
closed
2 years ago
2
how to fine-tune model
#43
MMMMichaelzhang
closed
2 years ago
5
a bug about val_list.txt
#42
vanetspark
closed
2 years ago
2
A possible bug in meldataset.py
#41
Charlottecuc
closed
2 years ago
1
how to change pitch
#40
MMMMichaelzhang
closed
2 years ago
3
pitch is not very correct when converting songs
#39
MMMMichaelzhang
closed
2 years ago
0
online flow inference
#38
Kristopher-Chen
closed
2 years ago
1
Duration is ~10% shorter that original
#37
skol101
closed
2 years ago
1
Advise on hyper param change
#36
skol101
closed
2 years ago
2
Which GAN vocoders shall work with what hyper params?
#35
skol101
closed
2 years ago
4
Using fine-tuned PWGan with trained model
#34
skol101
closed
2 years ago
1
Speaker selection and training on full VCTK set
#33
skol101
closed
2 years ago
2
Upsampling dataset?
#32
skol101
closed
2 years ago
1
Training questions: samples and resuming
#31
skol101
closed
2 years ago
1
What's the way to finetune pretrained StarGANv2 and ParallelWaveGAN ?
#30
skol101
closed
2 years ago
2
Is it possible to keep the timbre the same and only change the pitch
#29
980202006
closed
2 years ago
1
Non-parallel dataset
#28
kikirizki
closed
2 years ago
1
Jvs corpus
#27
supikiti
closed
2 years ago
0
Any reason why using consistency regularization?
#26
MingjieChen
closed
2 years ago
2
Muti-GPU support
#25
supernirmesh
closed
2 years ago
1
Why the norm consistency loss can help to preserve the speech/silence intervals of generated samples and thus decrease the noises?
#24
Charlottecuc
closed
2 years ago
1
Should I re-train ParallelWaveGan
#23
kikirizki
closed
2 years ago
1
training issue
#22
Kristopher-Chen
closed
2 years ago
1
Inference with noisy source
#21
Charlottecuc
opened
2 years ago
24
Training f0_mean IndexError: tuple index out of range
#20
jerrymatjila
closed
2 years ago
1
remove mapping network in training stage
#19
dragen1860
closed
2 years ago
1
load from my own training checkpoint failed
#18
dragen1860
closed
2 years ago
1
any tips on own dataset? say chinese content to japanese styel?
#17
dragen1860
closed
2 years ago
1
live infernce code?
#16
dragen1860
closed
2 years ago
1
Attempting live inference.
#15
Pathos0925
closed
2 years ago
3
Some doubt about the optimize step of style encoder
#14
980202006
closed
2 years ago
3
How to inference with unseen speakers?
#13
Charlottecuc
closed
2 years ago
1
Have you compared your model with PPG-based VC models?
#12
Charlottecuc
closed
2 years ago
2
Some doubt about the loss
#11
980202006
closed
2 years ago
2
Doubts about sampling rate
#10
980202006
closed
2 years ago
7
Can you provide the code for ASR and F0 network training?
#9
980202006
closed
2 years ago
39
Compatibility with custom vocoder checkpoints?
#8
Kreevoz
closed
2 years ago
7
Are there any details about the neutral to emotional conversion?
#7
980202006
closed
2 years ago
2
Some doubt about any to any voice conversion
#6
980202006
opened
2 years ago
98
How much loss model will converge?
#5
980202006
closed
2 years ago
4
Is there any guidance on distributed?
#4
980202006
closed
2 years ago
4
Update README.md
#3
ghost
closed
2 years ago
0
Develop
#2
yl4579
closed
2 years ago
0
Are there details about the generator?
#1
980202006
closed
2 years ago
7
Previous
Next