issues
search
jaywalnut310
/
vits
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
https://jaywalnut310.github.io/vits-demo/index.html
MIT License
6.73k
stars
1.24k
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How to change the speaker when inferencing?
#71
ZJ-CAI
closed
2 years ago
1
multi-speaker error
#70
sixyang
opened
2 years ago
3
How to get duration of each phoneme.
#69
tuannvhust
opened
2 years ago
1
Fail to run train.py
#68
l1006986533
closed
2 years ago
2
[Bug]`epoch_str` should be increased after loaded checkpoint
#67
cantabile-kwok
opened
2 years ago
2
DEBUG numba
#66
Ayushjaiswal12
opened
2 years ago
4
RuntimeError: "fill_cuda" not implemented for 'ComplexHalf'
#65
longglecc
closed
2 years ago
2
Correlation between characters error rate and noisy result
#64
kikirizki
opened
2 years ago
0
windows monotonic_align problem!
#63
SteveTanggithub
opened
2 years ago
4
Zero division error while training a hindi model
#62
tieincred
opened
2 years ago
16
Key error on tilda
#61
danielkrisp
opened
2 years ago
1
no inf checks were recoreded for this optimizer
#60
a2418701192
opened
2 years ago
0
Can I train on a Vietnamese custom dataset? If yes, can you specify how to do it?
#59
tuannvhust
closed
1 year ago
4
Multi speaker training error
#58
kumdori88
opened
2 years ago
3
infinite KL Divergence for low resource language data
#57
mehrzadai
opened
2 years ago
0
Help: monotonic_align !
#56
zhengyongchoa
opened
2 years ago
4
Could you please explain the KL loss in losses.py
#55
unrea1-sama
closed
2 years ago
2
about sampler buckets in dataloader
#54
forwiat
opened
2 years ago
1
Is it possible use same input generate fixed length of wav
#53
martin3252
closed
2 years ago
0
[Bug] 80000 exceeds legal port number range 0-65535
#52
OlaWod
opened
2 years ago
0
about multi-speaker data
#51
LH997
closed
2 years ago
4
very hard to construct a suitable environment
#50
coderyiyang
opened
2 years ago
1
Stochastic duration prediction failed for fastspeech2
#49
LEECHOONGHO
opened
2 years ago
4
why not use multi-scale D and loss NAN
#48
hdmjdp
opened
2 years ago
0
Can I use SDP for Fastspeech2?
#47
LEECHOONGHO
closed
2 years ago
1
How is the KL loss computed?
#46
cantabile-kwok
opened
2 years ago
7
Can't train with fp16 on Nvidia RTX3060
#45
thangnvkcn
opened
2 years ago
1
Training Time
#44
cantabile-kwok
opened
2 years ago
4
Can MultiHeadAttention replace with nn.MultiheadAttention?
#43
lucasjinreal
opened
2 years ago
0
questions about why not convert English words to phone?
#42
lucasjinreal
opened
2 years ago
1
Export the model to onnx format.
#41
mudong0419
opened
2 years ago
24
The segment_size in paper and code is different?
#40
xinghua-qu
opened
2 years ago
1
Training on GTX2080
#39
liuhaogeng
opened
2 years ago
2
no performance increase for multi-GPU
#38
FarisHijazi
closed
2 years ago
1
A simple multi-process version of preprocess.py
#37
OlaWod
closed
2 years ago
1
What tools do you use to create/split file lists for new dataset?
#36
skol101
opened
2 years ago
1
any suggestion for onnx exporting?
#35
wkkuniquegmail
opened
2 years ago
8
work around for pytorch stft backward bug.
#34
boltzmann-Li
opened
2 years ago
0
Add dataset support for aishell-3?
#33
luohao123
opened
2 years ago
0
Provide Full Pretrain models ?
#32
chazo1994
opened
3 years ago
5
poor performance on short phrases
#31
negidius
opened
3 years ago
8
vits_is_good
#30
MaxMax2016
closed
2 years ago
1
Pre-trained model link invalid
#29
Approximetal
opened
3 years ago
1
Training time on VCTK.
#28
mudong0419
opened
3 years ago
5
Question regarding symbols used
#27
akashicMarga
opened
3 years ago
2
Phonemizer is too slow
#26
Selimonder
closed
3 years ago
4
CPU infer slow
#25
OnceJune
closed
2 years ago
6
Training on Tesla K80
#24
StuteePatil
opened
3 years ago
3
How to fix the noise during inference time?
#23
xinghua-qu
closed
2 years ago
5
Leak memory when runing on CPUs
#22
ductho9799
opened
3 years ago
0
Previous
Next