I have a need to do annotation of classroom data. I would like to set up a recipe that would (a) preprocess the data using a pyannote-audio speech-identification model, and then (b) enable us to conduct multi-label classification on the identified segments.
I need a consultant to help me get that set up, and to do so within just a few days. Anyone able to support? Please reach out! Happy to discuss more details as appropriate and necessary. Rate / total cost negotiable.