ibab / tensorflow-wavenet

A TensorFlow implementation of DeepMind's WaveNet paper

ibab/tensorflow-wavenet Issues

problem on generate only noise
Updated a year ago5
Training wavenet to rap?
Updated a year ago
ModuleNotFoundError: No module named 'tensorflow.contrib'
Updated a year ago1
Project dependencies may have API risk issues
Updated 2 years ago
about loading VCTK_Corpus dataset？
Updated 2 years ago
No checkpoint found, despite running prevously
Updated 2 years ago4
Understanding convolution kernels in dilation layers
Updated 3 years ago4
Module 'tensorflow' has no attribute 'placeholder'
Updated 3 years ago8
TypeError: Value passed to parameter 'indices' has DataType float32 not in list of allowed values: uint8, int32, int64
Updated 3 years ago1
argmax or random.choice in generate?
Updated 3 years ago3
Why is there no activation function applied to the 1x1 conv that produces the dense output?
Updated 3 years ago
QUESTION How long does it take to generate one sample?
Updated 3 years ago1
Colab problem: continue previous training
Updated 3 years ago4
testing much worse than training?
Updated 3 years ago
Can anyone share a pre-trained wavenet model trained on complete VCTK corpus?
Closed 6 years ago1
How to stop and resume training
Updated 4 years ago2
generate.py very slow with GPU
Updated 4 years ago1
Problem on runing it on colab
Updated 4 years ago2
My loss function fluctuates like crazy.
Updated 4 years ago
I failed to download the dataset, how should I resolve the voice
Updated 4 years ago1
tensorboard result: the generated audio of generate.py is 0 seconds
Updated 4 years ago
TypeError: cast() missing 1 required positional argument: 'dtype'
Closed 4 years ago
How to generate Audio from text
Updated 5 years ago3
how dialated convolution actually work ?
Updated 5 years ago
The generated wav file is noise
Closed 5 years ago4
FileNotFoundError [WinError2]
Updated 5 years ago
Generated wav file is soundless?
Closed 5 years ago
Sanity check / overfit equivalent for music generation
Updated 5 years ago
What is the issue with training and inferencing on v100?
Updated 5 years ago1
How to use google dataset?
Updated 5 years ago
Parametric or concatenative TTS projects for comparision?
Updated 5 years ago
generate.py have the "SyntaxError: invalid syntax"
Updated 5 years ago
Feeding audio Waveform in every layer
Updated 6 years ago
TypeError whn running train.py
Closed 6 years ago3
wavenet implementation using tf.layers.conv1d
Updated 6 years ago1
tf.layers.conv1d(dilations)
Updated 6 years ago1
Possible to reduce time/step ? + gc_channels explanations
Updated 6 years ago
What is the main idea of global conditioning?
Updated 6 years ago2
Failed to create a directory: ./logdir\train\2018-09-11T16-06-25; No such file or directory
Updated 6 years ago1
NotFoundError: Failed to create a directory: outputs/tensorboard/TrafficSign/c1s_5_c2n_64_lr_0.0001_c1vl_16_rs_1_c2vl_32_c1nf_16_c1s_9_c1n_256_c2d_0.7_c2s_6-train--TrafficSign--1537421960.3313408; No such file or directory
Closed 6 years ago
Division corpus VCTK for training, testing and validate
Updated 6 years ago1
为什么我的loss降到1.2345之后上涨了现在又3.6578
Updated 6 years ago2
Why did we slice the output at every dilation layer?
Updated 6 years ago
Why convolute on the input_batch twice with different activation function, rather than convolute once and activate with different function
Closed 6 years ago5
dilations in wavenet_param.json
Updated 6 years ago
biases vs no biases
Updated 6 years ago
is there some pre-models?
Updated 6 years ago
Realistic music generation
Updated 6 years ago1
Weights in one layer do not change
Updated 6 years ago
Bus Error: 10
Updated 6 years ago