naxingyu / opensmile

A github repo of the openSMILE feature extraction tool.
http://www.audeering.com/research/opensmile
Other
214 stars 79 forks source link

OpenSMILE in real-time #36

Open viditjain99 opened 4 years ago

viditjain99 commented 4 years ago

Is it possible to use openSMILE in real-time with python to extract features on the fly to perform real-time processing?

Ehsan-Nirjhar commented 4 years ago

Yes, you need to install it with portaudio

viditjain99 commented 4 years ago

I installed it with portaudio, however, the features are generated once the live audio recording has finished. Is there a way to output features simultaneously while recording the live audio?

chausner-audeering commented 3 years ago

Real-time processing is supported and features should get generated continuously during recording, not only afterwards.

To use openSMILE from within Python, you may want to check out the SMILEapi Python wrapper that is part of the recently released version 3.0. There is also a simpler standalone Python package which might work for you.

krishna51119 commented 3 years ago

@chausner-audeering Sir How to use this code structure after installing opensmile using pip

opensmile_call = exe_opensmile + " -C " + path_config + " -I " + infilename + " -O " + outfilename

I have downloaded the opensmile but dnt know how to install it in windows,,,plz guide