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
Is it normal to wait a long time between each epoch？
#122
HuaHuaOfficial
opened
1 year ago
4
Inference result is not as good as the demo
#121
ali-elkahky
opened
1 year ago
5
FP32 training and alternative models
#120
NikitaKononov
opened
1 year ago
0
Use config boundaries instead of hardcoded
#119
nikich340
opened
1 year ago
0
Reduce RAM usage: remove excess workers
#118
nikich340
opened
1 year ago
3
Not all .wav files generate corresponding spec.pt
#117
anitman
opened
1 year ago
2
[Question] How many iterations for the available pretrained model?
#116
shivammehta25
opened
1 year ago
3
colab进行Multi Speaker测试时，出现错误
#115
sun-rabbit
opened
1 year ago
1
colab上无法运行测试
#114
sun-rabbit
opened
1 year ago
0
Sorry I have a Question about RuntimeError
#113
mao-mao-yu
closed
1 year ago
2
Question about VITS KL Loss Formula
#112
MMingabc
opened
1 year ago
1
How can we keep the output the same when the input is the same？
#111
Leo4zhou
closed
1 year ago
1
Ea 45 setup cpu inference
#110
arnasRad
closed
1 year ago
0
VCTK Multi Speaker Models Training Results (How many steps required for results like Pretrained)?
#109
athenasaurav
closed
1 year ago
5
Whether kl loss is negative will affect the model convergence?
#108
980202006
opened
1 year ago
0
When I train multispeaker get RuntimeError: cuDNN error: CUDNN_STATUS_INTERNAL_ERROR
#107
cliuxinxin
closed
1 year ago
2
Problems about training with multiprocess
#106
BrianWayland
opened
1 year ago
1
How to finetune the given pre-trained model?
#105
apzl
opened
2 years ago
6
what is difference between val.text and train.txt
#104
queechy
opened
2 years ago
0
CUDA ERROR!
#103
NK990
opened
2 years ago
1
Suggestion on Over-fitting?
#102
Ahmer-444
opened
2 years ago
0
How to conitnue trainig?
#101
NK990
closed
2 years ago
1
Fix typo in modules.py
#100
eltociear
opened
2 years ago
0
What is the relative position method
#99
TheHonestBob
opened
2 years ago
0
vits is awsome! Can vits train with emotional dataset?
#98
akfheaven
opened
2 years ago
2
你好，想拿来试试运行在colab，但是不成功
#97
upright2003
closed
1 year ago
2
torch.nn.modules.module.ModuleAttributeError: 'SynthesizerTrn' object has no attribute 'emb_g' 【anybody help me，please！】
#96
lunar333
opened
2 years ago
1
control and change the energy and pitch by manipulating the latent representation
#95
tuannvhust
opened
2 years ago
1
没人反馈这个语音API目前失效了吗
#94
xingyunlee12138
opened
2 years ago
0
没人反馈这个语音API目前失效了吗....
#93
xingyunlee12138
closed
2 years ago
1
Questions about the Korean datasets
#92
ORI-Muchim
closed
1 year ago
3
Question about strange voice
#91
panxin801
opened
2 years ago
0
Error on tensor size & How to config with 16KHz waves?
#90
voxServalG
opened
2 years ago
2
Is there any method which can adjust the speed of synthesized speech?
#89
guofengjpggwk
opened
2 years ago
1
size mismatch for enc_p.emb.weight
#88
kdrkdrkdr
closed
2 years ago
1
How many steps should we train to get the best results?
#87
futureaiengineeer
opened
2 years ago
12
I want to train VITS model for URDU language
#86
Muhammad-Afnan-Akram
opened
2 years ago
0
Mispronounce some words and 44,1 Khz audio
#85
tuannvhust
opened
2 years ago
2
Can I use it without GPU?
#84
itsdapi
opened
2 years ago
3
all loss keeps almost the same during training when using VITS to train multi-lingual datasets
#83
zhufeijuanjuan
opened
2 years ago
0
Can anyone explain me what the boundaries are for?
#82
tuannvhust
closed
2 years ago
2
Questions about 48k audio file train
#81
H4ppyB1rd
opened
2 years ago
6
Dev cython ext
#80
payonear
closed
2 years ago
0
有辦法做到單行指令轉換嗎?
#79
upright2003
opened
2 years ago
0
Something wrong hapeened to my interpreter?RuntimeError
#78
redmist328
closed
10 months ago
3
RuntimeError: The expanded size of the tensor (8192) must match the existing size (448) at non-singleton dimension 1. Target sizes: [1, 8192]. Tensor sizes: [448]
#77
zgfjzs
opened
2 years ago
0
RuntimeError: view_as_complex is only supported for float and double tensors, but got a tensor of scalar type: Half
#76
shoang22
closed
2 years ago
3
RuntimeError During Training
#75
QuellaMC
closed
2 years ago
1
Training error
#74
Eternity231
closed
2 years ago
6
AssertionError: 4D tensors expect 4 values for padding
#73
kagura114
closed
2 years ago
3
Previous
Next