search

jhetherly / EnglishSpeechUpsampler

Upsample speech audio in wav format using deep learning
MIT License
191 stars 33 forks source link

upsampling_audio_file #2

Open Alexander-flyer opened 6 years ago

Alexander-flyer commented 6 years ago

in upsampling_audio_file , there is a code here that puzzles me

true_wf = true_wf[:int(true_wf.size/INPUT_SIZE)*INPUT_SIZE]

I have modified the project that the model can upsampling a 8000hz audio to a 16000hz wav file. so true_wf is 8000 and INPUT_SIZE is 16000 in the processing final, int(true_wf.size/INPUT_SIZE)*INPUT_SIZE is 0, so the true_wf is None....... Is there any hint?

MagRac commented 4 years ago

Hey, I have the same problem, did you find any solution?