Harris Notes

Home

❯

concepts

❯

LLM Post Processing

LLM Post-Processing

May 02, 20261 min read

  • concept
  • general
  • process

LLM Post-Processing

Using a small general-purpose LLM (e.g., Llama 3B) after transcription to clean up filler words, correct formatting, and improve readability. Adds latency (~300-800ms) but improves output quality.

Related

local-offline-transcription whisper-model-variants llama-3b mlx-framework speak2 ollama


Graph View

  • LLM Post-Processing
  • Related

Backlinks

  • Local Offline Transcription
  • Getonit.ai
  • Llama 3B
  • MLX Framework
  • Speak2
  • 20260502-0656-local-llm-for-audio-transcription-on-mac-mini-m2-1
  • index

Created with Quartz v4.5.2 © 2026

  • GitHub
  • Discord Community