chrisdonahue/wavegan

Issues

• Broken Piano Dataset Download Link

  #120 opened 10 months ago by vitoc98
  0

• int() argument must be a string, a bytes-like object or a real number, not 'Tensor'

  #119 opened a year ago by viola911
  0

• Massive Tensorflow Error Message When Attempting to Train WaveGAN

  #118 opened 2 years ago by YongQinXu
  0

• OSS License compatibility question

  #117 opened 2 years ago by Ashley123456789
  0

• Error: stops training after 5 minutes

  #78 opened 5 years ago by Tylersuard
  3

• Tensorflow2.4 support

  #104 opened 4 years ago by luisarandas
  5

• Can't run

  #116 opened 3 years ago by okanduzyel
  4

• Overtraining

  #114 opened 3 years ago by JordanDavis-1
  2

• Invalid argument: You must feed a value for placeholder tensor 'ngl' with dtype int32

  #101 opened 4 years ago by mikemech83
  2

• Can't train the model

  #115 opened 3 years ago by Claire-Piquette
  0

• Metallic Comb-like Sound in Training Example

  #98 opened 4 years ago by torridgristle
  1

• Training starts but no updates are dumping to checkpoints?

  #112 opened 3 years ago by JordanDavis-1
  1

• Single-frequency noisy sound in the result

  #109 opened 3 years ago by RitoRitoni
  4

• Code for continue training model from last ckpt?

  #111 opened 3 years ago by RitoRitoni
  1

• Training higher quality audio for ~5 seconds

  #113 opened 3 years ago by mattgallivan
  0

• Reading WaveGAN models using Tensorflow C API

  #110 opened 3 years ago by JordanDavis-1
  0

• Can't get this to run anymore - Need information on environment

  #108 opened 3 years ago by go-dustin
  0

• Generate MFCC

  #107 opened 3 years ago by abedbanna
  0

• setup on colab

  #73 opened 5 years ago by MAnal0025
  18

• Multi-channel audio doesn't work with --data_num_channels 2 in Jupyter Lab

  #105 opened 4 years ago by Andy671
  1

• Can you fix collab

  #106 opened 4 years ago by joshuaword2alt
  0

• Transfer Learning using pre-trained checkpoints

  #100 opened 4 years ago by moiseshorta
  2

• Last layer of the generator in the CNN (size 16384)

  #103 opened 4 years ago by spagliarini
  1

• Can we change (increase) amount of training data in between sessions?

  #102 opened 4 years ago by mikemech83
  0

• much longer training times with phaseshuffle on

  #94 opened 4 years ago by markhanslip
  5

• shuffle buffer size is 4096 but I wish to use a dataset of 49k+ samples?

  #99 opened 4 years ago by mattjwarren
  0

• Cant train on 24-bit 44.1kHz wav files?

  #96 opened 4 years ago by benjimyma
  1

• Keras Loss implementation

  #95 opened 4 years ago by Arqit
  0

• Question regarding training efficiency

  #81 opened 5 years ago by xyz010
  2

• WaveGAN: Audio synthesis counter example where it fails for Broadband signals (Ambient noise)

  #88 opened 4 years ago by hinash88
  3

• Custom Drum Datasets

  #91 opened 4 years ago by thenapking
  2

• Can the specified target audio be generated?

  #93 opened 4 years ago by 1zxLi
  0

• Epoch size

  #92 opened 4 years ago by halameri
  3

• Is it possible to train specgan and wavegan pointing same train directory

  #90 opened 4 years ago by takeofuture
  0

• How to generate wav sample from trained chpt files v2, I cannot find object 'z:0' and 'G_z_spec:0'

  #89 opened 4 years ago by takeofuture
  1

• Dtest and Dtrain

  #87 opened 4 years ago by spagliarini
  2

• Inception Scores with Animal Vocalizations

  #83 opened 5 years ago by alexanderbarnhill
  2

• Can anyone help me with the generation of files

  #86 opened 5 years ago by vishal1o8
  2

• Training works perfectly on example datasets, fails on custom datasets

  #85 opened 5 years ago by Tylersuard
  2

• Standardized threshold for cat activation?

  #80 opened 5 years ago by Tylersuard
  2

• How to get latent space vector value for specific sound generated?

  #79 opened 5 years ago by moih
  6

• Error on Generation Colab notebook

  #84 opened 5 years ago by Tylersuard
  4

• How to convert a GAN to audio from image

  #82 opened 5 years ago by Tylersuard
  0

• How to get the discriminator?

  #72 opened 5 years ago by Reagan1947
  1

• Small dataset

  #77 opened 5 years ago by spagliarini
  0

• Results on 'continuous' speech (recommendations needed too)

  #76 opened 5 years ago by jvel07
  10

• Does it work for continuous speech?

  #75 opened 5 years ago by jvel07
  0

• tts

  #74 opened 5 years ago by mo-ezzat
  1

• Pre-Trained Discriminator

  #71 opened 5 years ago by haideraltahan
  0

• (ignore)

  #70 opened 5 years ago by michaelybecker
  0