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
6.91k
stars
1.27k
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
How can I know the number of steps?
#172
vidigal
opened
1 year ago
1
Cloning voices
#171
vidigal
opened
1 year ago
0
How to use ground truth durations to train vits?
#170
16dian11
closed
1 year ago
5
VITS2?
#169
OnceJune
opened
1 year ago
4
Question about the TextEncoder
#168
JohnHerry
opened
1 year ago
0
Why using z but not flow(z_p, spk_emb) for decoder ?
#167
thanhkm
opened
1 year ago
0
Korean Multi-speaker Model Convergence Failure
#166
heesuju
closed
1 year ago
4
Why use `randn_like` when sampling from latent distribution?
#165
bejaeger
opened
1 year ago
0
negative loss
#164
JunhaoHuang0615
opened
1 year ago
0
RuntimeError: DataLoader worker (pid 31433) is killed by signal: Aborted.
#163
JunhaoHuang0615
opened
1 year ago
2
Runtime error
#162
YTRemRem
closed
1 year ago
2
Problem when try to fine-turning on Google Colab: No kernel image
#161
K2O7I
closed
1 year ago
0
Training a 8k Model as LJSpeech.
#160
athenasaurav
opened
1 year ago
0
Computing power requirement
#159
JoyceMind
opened
1 year ago
3
Training is too slow. WHY?
#158
gandolfxu
opened
1 year ago
2
Any guidelines for tuning noise_scale_w?
#157
TinaChen95
opened
1 year ago
2
Problem with export model to onnx
#156
JoanisTriandafilidi
opened
1 year ago
2
About KL Divergence loss
#155
ylzz1997
opened
1 year ago
1
Purpose of sum(-1) in sqrt of spectrogram calculation
#154
m1rakram
opened
1 year ago
0
GPU multiprocess error
#153
deryaguler95
opened
1 year ago
1
How to train a multilingual model
#152
liuxiong21
opened
1 year ago
2
Fix typo in README.md
#151
santhoshtr
opened
1 year ago
0
Is punctuation an essential part of input when training TTS model?
#150
JohnHerry
opened
1 year ago
1
python build_ext don't automatically create dir
#149
gfreezy
closed
9 months ago
1
Are there any bug in voice_conversion (reverse True or False for source and target) ??
#148
yt605155624
opened
1 year ago
1
why raised grad.size warning?
#147
YooSungHyun
opened
1 year ago
0
ValueError: too many values to unpack (expected 2)
#146
wrl1224
opened
1 year ago
3
Do you have a more detailed video or steps?
#145
Knockoi
opened
1 year ago
1
Fixing srt misalignments
#144
rokasgie
closed
1 year ago
0
Remove testing artifacts
#143
rokasgie
closed
1 year ago
0
mac m1 inference
#142
zdj97
opened
1 year ago
2
torch2 compat
#141
yoinked-h
opened
1 year ago
1
How to generate a voice file ?
#140
hejinlong
closed
1 year ago
0
Problems with the pronunciation of one word.
#139
LanglyAdrian
opened
1 year ago
13
vits streaming inference demo code for you
#138
MaxMax2016
opened
1 year ago
1
The released model is trained using character?
#137
snsun
closed
1 year ago
1
Beware and Look out for some "People's doing" with this project.
#136
SKNIHC
opened
1 year ago
1
IndexError: Dimension out of range (expected to be in range of [-1, 0], but got 1)
#135
Arszr
closed
1 year ago
15
Training for custom dataset
#134
huydang2106
opened
1 year ago
4
Add onnx export
#133
NaruseMioShirakana
closed
1 year ago
0
Silence when generating audio
#132
LanglyAdrian
closed
1 year ago
5
在训练的时候我遇到了一些问题
#131
C9H20sx
opened
1 year ago
4
Best TTS based on BERT and VITS with some Natural Speech Features Of Microsoft
#130
MaxMax2016
opened
1 year ago
7
Errors encountered at the beginning of training. . . .（CUDA out of memory）
#129
Xiaoxiaosito
opened
1 year ago
1
How many training epochs are required to hear the content of synthetic speech clearly?
#128
GoArsenal
closed
1 year ago
2
> > @FanhuaandLuomu 输入为拼音的声母、韵母序列； 之前由于担心插入blank，会使输入序列变成2倍长度，导致工程实现中耗时变长，从而影响首包延时以及RTF。现在补上blank，没有出现发音问题了，加上blank后首包延迟为100ms，整体rtf为0.03的样子，还好。
#127
15755841658
opened
1 year ago
12
RuntimeError: [enforce fail at inline_container.cc:209] . file not found: archive/data/57749664
#126
sphiNur
closed
1 year ago
0
Dependencies
#125
BelT327l
opened
1 year ago
1
How to determine the model's accuracy based on log information?
#124
yz1392946854
opened
1 year ago
1
Multis-speaker identity degradation
#123
NikitaKononov
opened
1 year ago
4
Previous
Next