huawei-noah Speech-Backbones issues

huawei-noah / Speech-Backbones

This is the main repository of open-sourced speech technology by Huawei Noah's Ark Lab.

545 stars 112 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Generated Samples are noisy

#37 SandyPanda-MLDL opened 1 month ago
0
mels_mode generation

#36 Biyani404198 opened 4 months ago
0
Different Implementation of Diffusion Model

#35 siyag12 opened 7 months ago
0
GradTTS device compatibility

#34 bukhalmae145 closed 8 months ago
0
Not possible to build

#33 asusdisciple opened 8 months ago
1
Adding faster sampler

#32 shivammehta25 closed 9 months ago
2
Two questions about DiffVC

#31 huangf79 opened 10 months ago
0
Fix cropping mel logic

#30 chep0k opened 1 year ago
1
add `spk_emb_dim` and `n_spks` params to TextEncoder

#29 chep0k opened 1 year ago
1
A bug in model/tts.py

#28 chep0k opened 1 year ago
1
support for bigvgan

#27 eschmidbauer closed 1 year ago
2
Model training question

#26 Cpgrach opened 1 year ago
4
Typo in some equations in GradTTS paper

#25 cantabile-kwok closed 1 year ago
4
about diffVC on Mandarin datasets

#24 Theweekfoolish229 opened 1 year ago
4
Not able to generate audio using libritts of as good quality as using ljspeech

#23 Hertin closed 1 year ago
10
replace deprecated function `torchaudio.functional.istft` with `torch.istft`

#22 eschmidbauer opened 1 year ago
1
Finetuning a Grad-TTS model on a small dataset?

#21 godspirit00 opened 1 year ago
2
Why does the BNE-PPG-VC model in your demo perform better than the pre-trained model given in the original paper?

#20 jiazj-jiazj opened 1 year ago
1
Add DiffVC code

#19 ivanvovk closed 1 year ago
0
About the prior loss and MAS algorithm

#18 cantabile-kwok opened 1 year ago
2
Possibly missing __dict__ in the Projector class' constructor

#17 Sri-Harsha opened 2 years ago
0
How is `out_size` in `params` determined

#16 cantabile-kwok closed 2 years ago
2
Attention layer in GradTTS

#15 patrickvonplaten opened 2 years ago
2
Generated outputs sound robotic in some cases!

#14 aniketp02 opened 2 years ago
3
Diffusion loss not decreasing

#13 aniketp02 opened 2 years ago
1
About end2end implementation

#12 quangnh-2761 opened 2 years ago
10
ASR finetune ?

#11 Enescigdem opened 2 years ago
1
add implementation of SPIRAL

#10 wenyong-h closed 2 years ago
1
Multi-GPU training and expected epochs

#9 bieltura opened 2 years ago
5
Fine-tuning / Transfer Learning

#8 williamluer closed 2 years ago
11
Clipping distortion of the generated waveform

#7 WelkinYang opened 2 years ago
3
Add multi-speaker mode for Grad-TTS

#6 ivanvovk closed 2 years ago
0
Grad-TTS in multispeaker setting

#5 ajinkyakulkarni14 closed 2 years ago
2
[Errno 13] Permission denied: '/home/user/app/Grad-TTS/model/monotonic_align/core.c'

#4 AK391 closed 2 years ago
0
gradio demo

#3 AK391 closed 2 years ago
7
Grad-TTS: Colab Notebook

#2 AK391 closed 2 years ago
2
Add Grad-TTS code

#1 ivanvovk closed 2 years ago
1