descriptinc melgan-neurips issues

descriptinc / melgan-neurips

GAN-based Mel-Spectrogram Inversion Network for Text-to-Speech Synthesis

MIT License

980 stars 214 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

[CONTRIBUTION] Speech Dataset Generator

#48 davidmartinrius opened 9 months ago
0
update librosa.filters.mel and torch.stft to now release version

#47 LewisGet opened 1 year ago
0
Fix TypeError: mel() takes 0 positional arguments but 5 were given

#46 tuanio closed 1 year ago
0
How to normalize mel spectorgram extracted by Audio2Wav class?

#45 predawnang opened 1 year ago
0
How to measure the quality of synthetic audio with PESQ

#44 predawnang opened 1 year ago
0
Why is the generator loss continuously increasing instead of decreasing? Is continuous increase correct?

#43 jdwang125 opened 1 year ago
1
Why is D_fake calculated in "Train Generator" while D_real is calculated in "Train Discriminator"?

#42 jdwang125 opened 1 year ago
0
input Mel video spectrogram to generate audio

#41 Ivvvvvvvvvvy closed 1 year ago
2
Removing the last unnecessary downsampling in Discriminator

#40 stachu86 opened 1 year ago
0
Melgan multispaeker pretrained model fine-tuning with single speaker

#39 MuruganR96 opened 2 years ago
0
VQ-VAE Implementation

#38 dylanprins opened 2 years ago
0
what is the learning rate should be when finetune a small dataset on a base model

#37 Liujingxiu23 opened 3 years ago
0
Why perform Audio2Mel's method on extracting mel spectrogram?

#36 shawnbzhang opened 4 years ago
1
Problem in changing sample rate into 16k Hz

#35 xuexidi opened 4 years ago
3
Doubt about the defined hinge version Loss

#34 hhguo opened 4 years ago
2
No module named 'mel2wav'

#33 allenhung1025 closed 4 years ago
2
Generator architecture

#32 allenhung1025 opened 4 years ago
0
Some questions about your paper

#31 XinMing0411 opened 4 years ago
0
where can i find args.yaml file?

#30 sbkim052 opened 4 years ago
1
correct the usage of tail command in README.md

#29 yistLin opened 4 years ago
0
Where can I find the args.yml for the models provided in models/ folder?

#28 donand closed 4 years ago
1
How good are the pretrained model?

#27 BuaaAlban opened 4 years ago
1
wave data files

#26 lonnietc opened 4 years ago
0
noise vector in MelGAN and learning an accurate conditioning

#25 acids-ircam opened 4 years ago
0
why the loss_feat become larger during trainning？

#24 Liujingxiu23 opened 4 years ago
1
Good recover from real melspectrogram to audio, but problem in autoencoder.

#23 ericwudayi opened 4 years ago
3
How to load checkpoint to synthesis a speech from a mel spectrogram input?

#22 andro98 closed 4 years ago
1
What is "Spectral Normalization" mean in the paper?

#21 Liujingxiu23 opened 4 years ago
0
Is it possible to further improve the quality?

#20 xus-stack opened 4 years ago
0
Heavily CPU Dependent

#19 Teravus opened 4 years ago
5
Not able to start training. Give mel2wav not found error

#18 vashishtmarhwal closed 4 years ago
2
How to combine melGAN with feature predictor like FastSpeech or tacotron2?

#17 nikawool opened 4 years ago
2
Swapping Mel spectrogram with CQT spectrogram

#16 mcallistertyler closed 4 years ago
2
What is <root_data_folder>？

#15 nikawool closed 4 years ago
4
Tacotron2 + melgan = strange noise

#14 vcjob closed 4 years ago
1
Typo in arXiv paper

#13 JRMeyer closed 4 years ago
1
Problems when start training:ModuleNotFoundError: No module named 'mel2wav'

#12 HGZDG closed 4 years ago
5
How can I synthesize my own text to speech?

#11 ghost opened 5 years ago
13
What is the kernel size of dilated convolution?

#10 arijit17 opened 5 years ago
0
Missing sentences in paper v2.

#9 jeewenjie closed 4 years ago
1
How can I start training?

#8 deep-darkfantasy closed 4 years ago
7
Training time and how to start?

#7 omiano opened 5 years ago
1
In Windows, even when I pass nothing ("") to set_env.sh, I am getting GPU out of memory!

#6 khorshidisamira opened 5 years ago
1
SyntaxError: invalid syntax on torch.load(root / f"models/{model_name}.pt", map_location=device)

#5 khorshidisamira opened 5 years ago
2
about final loss?

#4 MorganCZY opened 5 years ago
16
about models/*.pt

#3 MorganCZY closed 5 years ago
7
Sample training dataset

#2 ghost closed 5 years ago
3
Inferencing script

#1 ghost closed 4 years ago
17