search

marcogdepinto / emotion-classification-from-audio-files

Understanding emotions from audio files using neural networks and multiple datasets.
GNU General Public License v3.0
404 stars 133 forks source link

Different versions of librosa lead to different results #70

Closed She-yh closed 1 year ago

She-yh commented 1 year ago

Dear author, Thank you for your share of this great respository. This helps me a lot as a beginner

I found that this model did not produce the correct results in my project. When I was solving the problem I found that, in newer version of librosa, the author replaced the default audio decoder with pysoundfile, this makes audio processing more accurate.

And I'm excited to share that with you image image

Thank you again for your work!