I use other library making sound segmentation.
But i have a problem like behind.
Input: cultoo.wav
Output: /speaker-diarization/lna/cultoo.lna
exception: AudioReader: sorry, audio files with multiple channels not supported
Traceback (most recent call last):
File "./generate_exp.py", line 264, in <module>
shift_dec_bord(lnas, arguments['--exppath'])
File "./generate_exp.py", line 181, in shift_dec_bord
num_models, l = _read_lna(lna)
File "./generate_exp.py", line 123, in _read_lna
with open(lna, 'r') as f:
That time, you solve easily like behind.
You have to use ffmpeg and -ac option.
ffmpeg -i cultoo.wav -ac 1 cultoo.wav