Giters
kuleshov
/
audio-super-res
Audio super resolution using neural networks
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
1124
Watchers:
25
Issues:
57
Forks:
203
kuleshov/audio-super-res Issues
Pre-trained models
Updated
8 months ago
How to install this now?
Updated
8 months ago
Comments count
2
Inference time
Closed
a year ago
Comments count
1
./singlespeaker.lr0.000300.1.g4.b64.meta does not exist.
Updated
a year ago
Comments count
14
Audio-super_res-test
Updated
a year ago
barti
Updated
a year ago
Installation is hard for average user.
Updated
a year ago
Comments count
2
Can I improve audio of a speech entirely - not interested in training
Updated
a year ago
Can this be used to actually upsample a low sample audio?
Updated
a year ago
Comments count
2
Unclear instructions with pretrained model
Updated
a year ago
Comments count
1
Create Conda Environment for Simple Installation
Closed
2 years ago
ImportError: cannot import name 'merge' from 'keras.layers'
Updated
2 years ago
Comments count
1
makefile error in speaker1
Closed
2 years ago
Comments count
1
makefile error
Closed
2 years ago
Comments count
1
OSError: File ./singlespeaker.lr0.000300.1.g4.b16/model.ckpt-209.data-00000-of-00001.meta does not exist.
Closed
2 years ago
Comments count
1
SNR decrease for speaker1
Closed
2 years ago
Comments count
1
is there any way to get this working on a google colab?
Closed
2 years ago
Comments count
1
Error at audiofilm.py: ValueError: Unexpectedly found an instance of type `<class 'tensorflow.python.framework.ops.Tensor'>`. Expected a symbolic tensor instance.
Closed
2 years ago
Comments count
6
Is the RNN model publicly available?
Closed
2 years ago
Comments count
1
Memory is not enough
Closed
2 years ago
Comments count
4
Colab?
Closed
2 years ago
Comments count
3
Where can the output be found?
Closed
3 years ago
Comments count
2
tensorflow.python.framework.errors_impl.InvalidArgumentError: All dimensions except 2 must match. Input 1 has shape [128 32 512] and doesn't match input 0 with shape [128 16 512]
Closed
3 years ago
Comments count
6
Reproducing results for multispeaker model
Closed
3 years ago
Comments count
7
parameters which gave best results on multi speaker
Closed
3 years ago
Comments count
1
LSTM kernel not compatible with cuDNN and GPU utilization is low
Closed
3 years ago
Comments count
1
pool_size and strides question
Closed
3 years ago
Comments count
2
ValueError: Shapes (4, 128, 128) and () are incompatible
Closed
3 years ago
Comments count
19
MULT-SPEAKER HELP
Closed
3 years ago
Comments count
1
Using LSD objective method to evalate the upsample wav, I can't get the same results on the paper.
Closed
3 years ago
Comments count
8
Incompatible shapes of X(data) and Y(label)
Closed
3 years ago
Comments count
5
Upload a pre trained model?
Closed
3 years ago
Comments count
9
Batch normalization is commented out - mistake?
Closed
3 years ago
Comments count
1
question of results in samples folder
Closed
3 years ago
Comments count
1
Pooling window and pooling strides
Closed
3 years ago
Comments count
1
Has anyone run through the Audio Super Resolution project code?
Closed
3 years ago
Comments count
1
Pull in fixes from Wuvist
Closed
3 years ago
Comments count
1
How to flip phase if designing ASR in frequency domain instead of time domain?
Closed
3 years ago
Comments count
1
What is the purpose of the patches?
Closed
3 years ago
Comments count
2
Error regarding 'dim_ordering'
Closed
3 years ago
Comments count
5
Error regarding
Closed
3 years ago
Comments count
4
OOM when trained on GeForce GTX 1080
Closed
3 years ago
Comments count
4
A bug in original paper ?
Closed
3 years ago
Comments count
1
About the dataset.
Closed
4 years ago
Building Speaker 1 Set
Closed
6 years ago
Comments count
1
make file does not download data
Closed
5 years ago
About the metrics SNR
Closed
5 years ago
Comments count
2
error when building mode
Closed
6 years ago
Building Data Set
Closed
6 years ago
Resize-convolution instead of subpixel convolution
Closed
6 years ago
Comments count
1
Previous
Next