I am working on a project, where I have to label the audio datasets which has thousands of data, each audio data is for one second. I have to label where it is in idle or event happening or noise. I used some tool like Audacity and Labelstudio, I can manually label the audio files which is in .wav but thousands of files it is very time consuming is there any alternative method for it, where I could label data efficiently. Now I was trying to write a python script for labelling but there was no luck, was struck in getting it an output viewing format. Could you please share your experience or any other solution for it as supervised learning .