search

resemble-ai / Resemblyzer

A python package to analyze and compare voices with deep learning
Apache License 2.0
2.79k stars 429 forks source link

Diarization issue #58

Open Manu21Iq opened 3 years ago

Manu21Iq commented 3 years ago

Diarization only applying for part of audio, I mean last few mins is not getting processed. I think that's because of below code in audio.py file:

Trim the end of the audio to have a multiple of the window size

wav = wav[:len(wav) - (len(wav) % samples_per_window)]

please let me know what i should do to get the complete audio diarization

teoh79 commented 2 years ago

Hello Manu, I face the same problem as the timestamp at the end of the diarization end 10s before te original file, example: Duration:60s Timestamps until 50s max Have you progress on this issue?

nehat005 commented 2 years ago

Anyone figure out why this necessary trimming of last few samples?