tensorflow-wavenet
tensorflow-wavenet copied to clipboard
ibab
A TensorFlow implementation of DeepMind's WaveNet paper
At line 68, change rmse to rms since librosa updated this function's name
Can someone explain to me the meaning behind the following parameters? residual_channels": 32, dilation_channels": 32, skip_channels": 512, I could not find a definition for what these parameters represent in the...
My computer is not very powerful and I don't have the resources available in my university, can someone or could the readme.md give us a link where we can download...
The performance of the network on GPUs seems to be lagging behind the CPU performance. I suspect that this is because the 2D convolution isn't designed to work efficiently if...
Root mean square error (rmse) has been renamed to rms from librosa ver 0.7.
In this PR, intra-op and inter-op threading are supported in the model. Moreover, profiling and new timer is also added. Readme file is also updated to show how to use...
Is there any option to generate audio wav file by giving text in generate.py
We've discussed the fact that one-hot encoding the input to the network is kind of weird, and that it would be more natural to use the waveform as a single-channel...
can someone tell me how this result came out? and if change to dialated to 2 ? what will happen?? conv = layers.Conv1D(1, 3, padding='causal', dilation_rate=1, bias_initializer=tf.keras.initializers.zeros) np.squeeze(sequence.numpy()) ->array([0. ,...
Hi! Does anyone get a FileNotFoundError when trying to run train.py? I have absolutely no clue what could cause this. If I run: python train.py --data_dir=corpus --logdir=log This error occurs:...
