hdubey

Hi Santi, Thanks for suggesting this. I just got the unsupervised MI training started. However, I am more interested in Supervised Speaker ID on Librispeech. When I do python spk_id/nnet.py...

Hi @santi-pdp I fixed the waveminionet issue. However, there seems to be a mandatory data "SPK2iDX", how to generate it for Librispeech? In below command, how can I get the...

* (HEAD detached at 4a98525) master remotes/origin/HEAD -> origin/master remotes/origin/lorelei remotes/origin/master remotes/origin/tensorflow remotes/origin/tf_clean

Thanks. I reinstalled the gcc. Now, new error appears: collect2: error: ld returned 1 exit status ../makefiles/default_rules.mk:35: recipe for target 'liblm.so' failed make[1]: *** [liblm.so] Error 1 make[1]: Leaving directory...

@tgaddair Is there any way to use the Learning rate schedular for pytorch with horovod? If we choose to not broadcast it, will it cause poor learning?