Closed umerjamil16 closed 2 years ago
Hi @umerjamil16,
Did you set svoice.C=3
? you should specify to how many channels you want to separate the input mixture.
Got it, its working fine now. Thanks for the quick reply.
@umerjamil16 can you share how did the training with librimix go ? with 3 speakers.
I trying to do the same.
Also, I would appreciate if you could share the config.yaml for 3speakers(librimix).
Thanks
Hello,
I am training model on Librimix 3 speakers dataset. I've also modified the make_debug.sh file for generating .json file in svoice/egs/debug/tr/ directory. However I am facing error as shown in below code (The model train perfectly for dataset of 2 speakers).
Would be greatful if someone can point me in a direction towards addressing the issue.