hdubey

Training PASE architecture for only Speaker ID using Librispeech data

4

Hi Mirco, Santi, Thanks again for this great contributions. I had a look at codes and paper. The architecture is interesting. I want to train this architecture on Librispeech for...

Hi, I tried to use the pre-trained model w/ biasing. I got the following error: DataLossError (see above for traceback): Unable to open table file segan_results/SEGAN-41700.data-00000-of-00001: Data loss: not an...

Installing error

8

I am installing one year ago version of essen with cuda 7.5 and cuda8.0 on a ubuntu with GPU. Got following error during install: "gcc: error trying to exec 'cc1plus':...

Hi, I have trained your model on VCTK and when I run evaluate I do not see any number or new files. I am interested to generate new audio using...

Adding MIT licence

2

Hi Mirco, Thanks for making this tool available. Can you please add some license perhaps MIT license that can allow me to use this repo for some non-academic projects?

Train, Validation and test set for VoxCeleb1 and voxCeleb2

1

Hi, I am working on DNN based speaker ID using voxCeleb. How do you define train, validation and test sets for both datasets. I can see identification file list for...