issues
search
yl4579
/
StyleTTS
Official Implementation of StyleTTS
MIT License
385
stars
62
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Is there a first-stage pretrained model?
#77
cnint0627
opened
2 days ago
0
can't import mask_from_lens from monotonic_align
#76
cnint0627
opened
3 days ago
0
amazing work,can it support that generate the phoneme delayed time sequence?
#75
CasonTsai
opened
1 month ago
0
MelSpectrogram() and unspecified sampling rate
#74
dsplog
opened
4 months ago
0
Voice Quality issue using Librispeech
#73
Anshu-Kumar-1
opened
6 months ago
0
Marathi Support ?
#72
raushanagrawal
opened
7 months ago
0
Is the uv detector trained in the pretrained pitch detector?
#71
auspicious3000
opened
7 months ago
0
Has anyone had this problem when converting to onnx?
#70
bobo-paopao
opened
7 months ago
0
S2S
#69
pawanhv
closed
8 months ago
1
StyleTTS 2
#68
fakerybakery
closed
8 months ago
1
continue correct number of epoch from pretrained
#67
magicse
opened
9 months ago
0
Update train_second.py
#66
magicse
closed
9 months ago
0
question
#65
magicse
closed
9 months ago
2
Pre-training model sound quality issues
#64
gachaun
closed
9 months ago
5
train on ESD
#63
bobo-paopao
closed
9 months ago
1
Inference exact time for each word
#62
enla51
closed
10 months ago
5
Question: Fine tuning LibriTTS with StyleTTS
#61
Yahya-khodr
closed
10 months ago
5
The pronunciations of single words or short words is poor?
#60
GuangChen2016
closed
10 months ago
1
Training Model with new Dataset
#59
Yahya-khodr
closed
11 months ago
0
Training the model
#58
Yahya-khodr
closed
11 months ago
1
what is the mean=-4 and std=4 meannig?
#57
skysbird
closed
11 months ago
1
First stage alignment training failed when TMA_CEloss=True
#56
auspicious3000
closed
11 months ago
2
style encoder inconsistency
#55
auspicious3000
closed
11 months ago
1
batch size and number of epochs for large dataset
#54
auspicious3000
closed
11 months ago
1
多卡训练的问题
#53
bobo-paopao
closed
11 months ago
5
About train on Vietnamese Dataset
#52
christopherohit
closed
11 months ago
1
hi，如果使用v4000 单卡 训练LibriTTS数据集，显卡内存只有16G， batch_size只能设置为8，训练时常大概为多长呢？谢谢
#51
bobo-paopao
closed
1 year ago
1
Need help for training
#50
nhanhttrong
closed
12 months ago
5
s2s loss 和mono loss在第一阶段的训练中一直为0
#49
bobo-paopao
closed
1 year ago
1
how to Inference
#48
luwentao1989
closed
1 year ago
1
Source of Hifigan checkpoints?
#47
kmn1024
closed
1 year ago
1
pretrained model of stage 1
#46
nhanhttrong
closed
1 year ago
0
Can you offer the loss log of style tts
#45
hdmjdp
closed
1 year ago
1
asr phone dict different from this
#44
hdmjdp
closed
1 year ago
1
about ASR model
#43
hdmjdp
closed
1 year ago
1
Would you recommend changing the code in the inference notebook when running a PL-BERT finetuned model?
#42
ghost
closed
1 year ago
1
error while running train_second.py (caused by size mismatch)
#41
ghost
closed
1 year ago
2
Code for Emotional Speech Synthesis
#40
satani99
closed
1 year ago
1
Questions about the Evaluations
#39
Zhongxu-Wang
closed
1 year ago
1
turns out your code doesn't join the read wav paths from train_list.txt file with the dataset path (the location of train_list.txt)
#38
ghost
closed
1 year ago
0
running train_first.py raises error
#37
ghost
closed
1 year ago
3
Any-to-any and emotion examples
#36
sleimanitani
closed
1 year ago
6
Phoneme sequence padding
#35
WorkingJack
closed
1 year ago
3
Fixing librosa compatibility issue and UTF-8 issue
#34
Artyom17
closed
1 year ago
0
What's r1_reg loss?
#33
splinter21
closed
1 year ago
1
Probleam about data processing
#32
Zhongxu-Wang
closed
1 year ago
1
crashes during training
#31
ppisljar
closed
1 year ago
4
Why don't use "attention_weight" in train_first.py ?
#30
dy2009
closed
1 year ago
1
Why I can't use your mel to train HiFi-Gan Vocoder ?
#29
dy2009
closed
1 year ago
1
f0_extractor ?
#28
dy2009
closed
1 year ago
0
Next