auspicious3000 / SpeechSplit

Unsupervised Speech Decomposition Via Triple Information Bottleneck
http://arxiv.org/abs/2004.11284
MIT License
644 stars 92 forks source link

There is exception when i run the main.py! How can i fix it? #13

Closed niu0717 closed 4 years ago

niu0717 commented 4 years ago

image The dateset is your provided training data . How can i fix it? Thx :) !

niu0717 commented 4 years ago

https://github.com/auspicious3000/SpeechSplit/blob/1ae3c6c02ea606d5dd024f2395902f531b875227/data_loader.py#L107

The len(aa) is a scala, but the type of len_crop is ndArray. The result of 'len(aa) - len_crop' is also ndArray. However, the second params of np.random.randint() need a int value. Maybe there are some problems?

auspicious3000 commented 4 years ago

please update numpy or use len_crop[0]