p0p4k pflowtts_pytorch issues

p0p4k / pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper

https://neurips.cc/virtual/2023/poster/69899

MIT License

196 stars 28 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Added 2nd-order Heun's method and midpoint method for ODE sampling

#45 FENRlR closed 6 days ago
1
Segmentation fault while training on a new language

#44 bharathraj-v closed 1 month ago
20
Compare to Vits2

#43 HuuHuy227 opened 2 months ago
0
Fix typo in export.py

#42 bharathraj-v closed 2 months ago
1
How to run cli.py?

#41 mumuyeye opened 3 months ago
2
High duration loss

#40 w11wo opened 3 months ago
17
Hi, Can I make longer pauses between sentences in pflow? Is it possible or not?

#39 Oleksandr2505 closed 1 week ago
2
phoneme question

#38 yiwei0730 opened 3 months ago
7
about zero-shot inference

#37 0913ktg opened 4 months ago
31
2nd-order Heun's method for ODE sampling

#36 kunibald413 closed 6 days ago
2
About model implementation differences

#35 sourcesur opened 4 months ago
3
Is there any already trained english (or any other) model, that we can test, maybe based on ljspeech dataset?

#34 Oleksandr2505 opened 4 months ago
1
Error while finetuning multi speaker from pretrained model

#33 ken2190 opened 4 months ago
4
Does model output phoneme-level timing info ?

#32 lumpidu opened 4 months ago
1
NAN loss

#31 0913ktg opened 4 months ago
8
about n_spks

#30 0913ktg opened 4 months ago
6
not import monotonic_align at every forward pass

#29 Tera2Space closed 4 months ago
2
noise scaled mas

#28 Tera2Space closed 4 months ago
4
Error when training single speaker model from scratch

#27 ken2190 closed 5 months ago
2
Works only with n_feats=80

#26 patriotyk opened 5 months ago
6
Error when finetuning multi speaker from pretrained model

#25 ken2190 closed 5 months ago
1
Crash in MAS

#24 patriotyk opened 5 months ago
23
Unused model

#23 Tera2Space closed 5 months ago
3
AlignerNet

#22 Tera2Space closed 5 months ago
8
Loss masking?

#21 epii2zero closed 6 months ago
15
Distortion of audio

#20 egorsmkv opened 6 months ago
2
Noise in e2e branch

#19 Tera2Space closed 6 months ago
2
Prior or encoder Loss

#18 epii2zero closed 6 months ago
2
How to perform fine-tuning?

#17 HobisPL closed 4 months ago
7
Positional encoding

#16 sverdoot opened 6 months ago
1
pflow performance

#15 yiwei0730 closed 3 months ago
0
descript/encodec is too slow in dataloader

#14 vuong-ts opened 7 months ago
7
it's possible voice change to clone new voice with just one wav file or more ?

#12 lpscr closed 7 months ago
4
Jump in sub_loss/train_dur_loss_step

#11 vn09 opened 7 months ago
6
The pre-trained hifigan model

#10 XierHacker closed 7 months ago
3
_clean_text is returning invalid symbol

#9 eschmidbauer opened 7 months ago
6
Multi gpu training; RuntimeError: [...] LightningModule has parameters that were not used in producing the loss returned by training_step.

#8 kunibald413 opened 7 months ago
3
TypeError: pflowTTS.synthesise() got an unexpected keyword argument 'spks'

#7 kunibald413 opened 7 months ago
2
possible custom model inference issue

#6 kunibald413 opened 7 months ago
1
pflow/data/text_mel_datamodule.py __getitem__

#5 zidsi closed 7 months ago
7
remove duplicate

#4 Tera2Space closed 6 months ago
1
How ready is multispeaker training?

#3 kunibald413 closed 7 months ago
1
Make it multi-language?

#2 zidsi opened 7 months ago
10
requirements & phonemizer ?

#1 zidsi closed 7 months ago
2