CountNet icon indicating copy to clipboard operation
CountNet copied to clipboard

Deep Neural Network for Speaker Count Estimation

Results 4 CountNet issues
Sort by recently updated
recently updated
newest added

``` $ docker run -i countnet python predict.py --model CRNN examples/5_speakers.wav Unable to find image 'countnet:latest' locally docker: Error response from daemon: pull access denied for countnet, repository does not...

Hey! I really love your work and I'm wondering whether you can provide the training data you synthesized from _LibirSpeech clean-360_ dataset? That would help a lot!

Also optimise Dockerfile for quick rebuilds. Also add multiple input files support to `predict.py`. Is it expected that the estimate for 5 speakers example is 6?

currently docker build is broken due to the missing requirements.txt