Giters
drethage
/
speech-denoising-wavenet
A neural network for end-to-end speech denoising
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
672
Watchers:
19
Issues:
42
Forks:
165
drethage/speech-denoising-wavenet Issues
requirements doesn't include TF
Updated
9 months ago
Comments count
2
Has someone do inference (denoise an audio) successfully?
Updated
a year ago
Comments count
2
Denoised Speech is silence
Updated
2 years ago
Comments count
3
Implement the code
Updated
2 years ago
Can't fine model
Updated
3 years ago
Comments count
4
out memory?
Updated
4 years ago
Comments count
5
Getting Out-of-memory (OOM) error on running the model on GPU.
Closed
7 years ago
Comments count
5
sor with shape[655360,31,1,256] and type float on /job:localhost/replica:0/task:0/device:CPU:0 by allocator cpu
Updated
4 years ago
Comments count
3
Model just stops when denoising
Updated
4 years ago
Comments count
4
Readme requirements
Updated
5 years ago
Comments count
7
Difference Between this and others
Updated
5 years ago
parameter size
Updated
5 years ago
Bad denoising results on the provided model
Updated
5 years ago
Comments count
2
cudnn version
Updated
5 years ago
TypeError: 'float' object cannot be interpreted as an integer
Updated
5 years ago
Comments count
7
Not using XLA:CPU for cluster because envvar TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set. If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU. To confirm that XLA is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile.
Updated
5 years ago
No version in python3 ?
Updated
5 years ago
Comments count
1
No optparse in python3
Updated
5 years ago
type error
Updated
5 years ago
Comments count
1
PESQ and STOI
Updated
5 years ago
Denoised audio 0db on NSDTSEA
Updated
5 years ago
Comments count
5
Any way to prevent early stopping?
Updated
5 years ago
Comments count
1
index 2 is out of bounds for axis 0 with size 2
Closed
5 years ago
Meaning of "in_memory_percentage" config parameter
Updated
5 years ago
Comments count
2
Nvidia driver version exception
Updated
6 years ago
Comments count
1
What kind of HW is needed to run the "best performing model"?
Updated
6 years ago
Comments count
2
About get_dataset(config, model) function
Updated
6 years ago
speed up training
Closed
7 years ago
Comments count
3
Trying to reproduce the results/ Error with pygpu
Updated
6 years ago
ValueError: output of generator should be a tuple (x, y, sample_weight) or (x, y). Found: None
Closed
6 years ago
Comments count
3
How you got the best performing model
Updated
6 years ago
Denoised audio has 0db?
Updated
6 years ago
Comments count
3
How to predict not a single value but a distribution as in original Wavenet?
Closed
6 years ago
Comments count
3
Any other audio format supported by Wavenet model (like .mp3) other than .wav?
Closed
7 years ago
Comments count
2
Why does the trained model need clean audio files for inferencing on the same noisy audio files?
Closed
7 years ago
Comments count
3
Value error
Closed
7 years ago
got wrong array shape
Closed
7 years ago
Comments count
3
Where is the pre-trained model?
Closed
7 years ago
Comments count
1
Is there any possibilities to change into Tensorflow model?
Closed
7 years ago
Comments count
1
Issue on using the trained model
Closed
7 years ago
Comments count
6
Method to evaluate enhanced speech
Closed
7 years ago
Comments count
2
Some samples of the denoised speech wave is missing in the end of the speech
Closed
7 years ago
Comments count
1