I used SillyTavernAI to make a transcription scrubber with a Large Language Model (LLM). It perfectly complements STT (Speech-to-Text) engines like Whisper and helps you to structure your spoken notes.

Follow along, the first part of the tutorial is super simple and does not require a GPU or even a powerful computer!

Audio Scrubber Character file:
https://gist.github.com/AIWintermuteA...
https://www.chub.ai/characters/Winter...

Or paste this into Import Content from External URL in SIllyTavernAI (Cloud Icon in Character Management):
WintermuteAI/audio-scrubber-c32f9099

TheBloke/Orca-2-7B-GGUF
https://huggingface.co/TheBloke/Orca-...

You won't believe how fast it is | Raspberry Pi Speech-to-Text
   • You won't believe how fast it is | Ra...  

How I made a custom GPT | With web search, knowledge database and character personas
   • How I made a custom GPT | With web se...