Are there any open source models that do diarization and transcription?

Question

Every time I look up speech-to-text, all I get are diarization or transcription models, but not both. Are there any models that say, process a conversation wav/mp3/whatever file and transcribe it with the relevant speaker labels?

Answer 1

Here you have many speeches from 24 actors that could work:

https://www.kaggle.com/datasets/uwrfkaggler/ravdess-emotional-speech-audio

Also a dataset with 60 different speakers and 30000 audio samples:

https://github.com/soerenab/AudioMNIST