search

keunwoochoi / music-auto_tagging-keras

Music auto-tagging models and trained weights in keras/theano
MIT License
616 stars 142 forks source link

audio_processor.py bug #11

Closed dojochu closed 7 years ago

dojochu commented 7 years ago

In compute_melgram() function, just need to make sure you provide integer values for the indices

Adapt Line 31: src = src[(n_sample - n_sample_fit) / 2:(n_sample + n_sample_fit) / 2]

To: src = src[int((n_sample - n_sample_fit) / 2):(int(n_sample + n_sample_fit) / 2)]

keunwoochoi commented 7 years ago

I think both n_sample and n_sample_fit are always integers.