How do i use it for emotion recognition?
#11
by
Thej6969
- opened
how do i use this model for recognising emotion of audio?
You could fine-tune it on an emotion recognition dataset as explained here: https://huggingface.co/docs/transformers/en/tasks/audio_classification
This approach does not seem to work for the actual AST model ("MIT/ast-finetuned-audioset-10-10-0.4593")