About this document

Audio Classification with Librosa & PyTorch by saiprudhvibodempudi11 is a document available to read on EtoBox.

The document discusses environmental sound classification using the librosa and pytorch libraries. It describes preprocessing audio data by extracting mel spectrogram features from sound clips, converting the spectrograms to images, and loading the data into pytorch. A pre-trained ResNet34 model is used for classification, trained on the ESC-50 dataset for 50 epochs.

Author

saiprudhvibodempudi11

Language

EN