aishoot / concurrent_speakers_counter Goto Github PK

View Code? Open in Web Editor NEW

22.0 3.0 6.0 4.44 MB

Estimate the number of concurrent speakers from single channel mixtures to crack the "cocktail-party” problem.

Jupyter Notebook 99.48% Python 0.52%

cocktail-party-problem speech-seperation speaker-count single-channel-speech-separation

concurrent_speakers_counter's People

Contributors

Stargazers

Watchers

Forkers

wushichao zane678 userzhongjieli dendisuhubdy rickzhuym fwl2000

concurrent_speakers_counter's Issues

file : /stft.mat'

This error appears with me, and I can't find this file : FileNotFoundError: [Errno 2] No such file or directory: 'data/stft.mat'

Model Training

I want to know how the model is being trained, here you are using a pre-trained model. I want to know the code behind the training.

ImportError: Could not find: nvcuda.dll

I get the following error:

ImportError: Could not find 'nvcuda.dll'. TensorFlow requires that this DLL be installed in a directory that is named in your %PATH% environment variable. Typically it is installed in 'C:\Windows\System32'. If it is not present, ensure that you have a CUDA-capable GPU with the correct driver installed.

Any idea how to resolve it?
Thanks.