search

tyiannak / pyAudioAnalysis

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications
Apache License 2.0
5.88k stars 1.2k forks source link

Wrong result of the classification example, why?.. #103

Open Nokimann opened 7 years ago

Nokimann commented 7 years ago

I installed this library today

installation so far... on the command prompt, pip install numpy matplotlib scipy sklearn hmmlearn simplejson eyed3 pydub git clone https://github.com/tyiannak/pyAudioAnalysis.git

wrote down the example code in the 'An audio classification example' got an error about 'ffmpeg' then fixed it followed by the site: http://www.wikihow.com/Install-FFmpeg-on-Windows

And then executed the code again. But the result was # (-1, -1, -1) instead of (0.0, array([ 0.90156761, 0.09843239]), ['music', 'speech']).

All things were done on 'windows 10' and 'jupyter notebook python 2'

What is the problem of it ? and What should I do?

miladcheraghi commented 7 years ago

i write command for audio classification in terminal (Ubuntu) and that was correct but when i write in python file and show result in django template it show (-1, -1, -1) ... and i dont know why?? please help us...

Nokimann commented 7 years ago

I found out the error. There is no file named 'classifierData.' In my opinion, the developer (tyiannak) should check and upload the file, or where could I download the file, 'classifierData'?

haribaskar commented 7 years ago

from pyAudioAnalysis import audioTrainTest as aT Result,P,classNames=aT.fileClassification("/home/hari/happy/hubble/demo_audio/pyAudioAnalysis/data/recording1.wav", "svmSMtemp","svm")

Check whether the following models present in the proper directory, "svmSMtemp", " svmSMtemp.arff", " svmSMtempMEANS"