Skip to content

Issues: descriptinc/melgan-neurips

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

31 Open 15 Closed
31 Open 15 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

The generated audio length is one second shorter
#50 opened Dec 22, 2024 by hahahaha2019310241
For Ready-to-use env.yaml for training. (Create new file <<melgan3.6_env.yaml>> and paste this text, Required python 3.6)
#49 opened Dec 19, 2024 by iamshreeji-copy1
[CONTRIBUTION] Speech Dataset Generator
#48 opened Feb 29, 2024 by davidmartinrius
How to normalize mel spectorgram extracted by Audio2Wav class?
#45 opened May 10, 2023 by predawnang
How to measure the quality of synthetic audio with PESQ
#44 opened May 5, 2023 by predawnang
Why is the generator loss continuously increasing instead of decreasing? Is continuous increase correct?
#43 opened Mar 27, 2023 by jdwang125
1
Why is D_fake calculated in "Train Generator" while D_real is calculated in "Train Discriminator"?
#42 opened Mar 27, 2023 by jdwang125
Melgan multispaeker pretrained model fine-tuning with single speaker
#39 opened Sep 29, 2022 by MuruganR96
VQ-VAE Implementation
#38 opened Feb 7, 2022 by dylanprins
what is the learning rate should be when finetune a small dataset on a base model
#37 opened Jan 26, 2021 by Liujingxiu23
Why perform Audio2Mel's method on extracting mel spectrogram?
#36 opened Nov 24, 2020 by shawnbzhang
1
Problem in changing sample rate into 16k Hz
#35 opened Nov 16, 2020 by xuexidi
3
Doubt about the defined hinge version Loss
#34 opened Sep 10, 2020 by hhguo
2
Generator architecture
#32 opened Sep 9, 2020 by allenhung1025
Some questions about your paper
#31 opened Sep 7, 2020 by XinMing0411
where can i find args.yaml file?
#30 opened Sep 2, 2020 by sbkim052
1
How good are the pretrained model?
#27 opened Jun 18, 2020 by BuaaAlban
1
wave data files
#26 opened Jun 11, 2020 by lonnietc
noise vector in MelGAN and learning an accurate conditioning
#25 opened Jun 10, 2020 by acids-ircam
why the loss_feat become larger during trainning？
#24 opened May 19, 2020 by Liujingxiu23
1
Good recover from real melspectrogram to audio, but problem in autoencoder.
#23 opened May 5, 2020 by ericwudayi
3
What is "Spectral Normalization" mean in the paper?
#21 opened Apr 20, 2020 by Liujingxiu23
Is it possible to further improve the quality?
#20 opened Apr 9, 2020 by xus-stack
Heavily CPU Dependent
#19 opened Mar 5, 2020 by Teravus
5
How to combine melGAN with feature predictor like FastSpeech or tacotron2?
#17 opened Feb 25, 2020 by nikawool
2
ProTip! Exclude everything labeled bug with -label:bug.