Anyone please answer if you know....i've been try for training speech recognition with tflite-model-maker (i know it just like an audio classification to recognize ia it 'dang', 'good', or 'ugly' words..not like whisper from open ai). now i want inference it with mediapipe, how can i do it??
@JuanDGaravito9 ай бұрын
Hi, I'm loving these great series of videos! I'm struggling about creating my own model to classify some music genres (e.g. punk vs pop). How do I train my own model for this? Thanks a lot and I hope you keep posting videos like this!
@ptruiz_google9 ай бұрын
I believe the TensorFlow Lite Model Maker app should be able to do audio classification training for you :) You'll just need your own data sorted based on the label you want to give each item.
@JuanDGaravito9 ай бұрын
@@ptruiz_google I'll try that out, thank you very much!