Audio time domain deep learning classifier

I'm looking for someone who can help create an Audio Time Domain Deep Learning Classifier. The desired output of the classifier is multiclass classification, and I have a dataset already prepared for training the model. The preferred programming language for implementation is Python. This project is to support an ongoing research, the end result would be an audio classification pipeline that is fully in the time domain. Pipeline looks as follows: data ingestion, preprocessing, transformer classifier to ingest data in time domain and produce event classifications. After event classifications are produced we will combine sequence of events classified per audio file to produce a single classification per file this will also be via a classifier.