How best to retrain or refine faster whisper model for specific data

[JohnnyGeraldPeterson]

Title pretty much says it all. I would like to finely tune this model for specific kinds of audio data, and I am unsure where to begin. Are there any resources for this? Any existing guides you would recommend? If not, then perhaps this can become a discussion for the issue. Thank you all!

[MahmoudAshraf97]

faster whisper is an inference engine for whisper models, so you have to finetune a whisper model first and then convert it to CT2 format and use it with faster whisper, This is a good starting point, also check the issues for possible issues you may face after finetuning