adobe-research/DeepAFx-ST

How can I process an entire audio file?

CyberLykan opened this issue · 1 comments

I want to process an entire audio file, but the code currently uses only five seconds from the input and reference.

When I comment these out in process.py, it returns the processed file, but the audio seems to appear more than once in the output.
x_24000 = x_24000[0:1, : 24000 * 5]
r_24000 = r_24000[0:1, : 24000 * 5]

I might have found something. Change these two lines to the following:
x_24000 = x_24000[0:1, : x_24000.shape[-1] // 2]
r_24000 = r_24000[0:1, : r_24000.shape[-1] // 2]