taoruijie / speaker-recognition-demo Goto Github PK

Traceback (most recent call last):
File "demoSpeakerNet.py", line 53, in
score = [float(numpy.round(- torch.nn.functional.pairwise_distance(feat_enroll.unsqueeze(-1), feat_test.unsqueeze(-1).transpose(0,2)).detach().numpy(), 4))]
TypeError: only size-1 arrays can be converted to Python scalars

The parent repository is using an MIT license. Can we assume that this repo is also licensed to MIT?

I wanted to test the demo recognition with my test audios, but an error occured the Warning goes below:
Traceback (most recent call last):
File "E:\SpeakerRecognitionDemo-main\demoSpeakerNet.py", line 53, in
score = [float(numpy.round(-torch.nn.functional.pairwise_distance(feat_enroll.unsqueeze(-1), feat_test.unsqueeze(-1).transpose(0,2)).detach().numpy(), 4))]
TypeError: only size-1 arrays can be converted to Python scalars

I didnt change the code, can you help?