verbatim-dicta/QUICK_START.md

Quick Start Guide

Dutch Language (Nederlands)

Basic Dutch Transcription

./RUN_DUTCH.sh

• ✅ GPU-accelerated (RTX 4060 Ti)
• ✅ Sentence extraction (complete zinnen)
• ✅ Base model (goede balans snelheid/nauwkeurigheid)

Dutch with LLM Analysis

./RUN_DUTCH_LLM.sh

• ✅ All features from basic version
• ✅ Fact-checking van uitspraken
• ✅ Automatische vraag generatie
• Uses llama3.2:latest model

Save to File

./RUN_DUTCH.sh --output transcript.txt
./RUN_DUTCH_LLM.sh --output enriched.txt

---

English Language

Basic English Transcription

./RUN_GPU.sh

English with LLM

./RUN_GPU.sh --enable-llm

---

Other Languages

Spanish

./RUN_GPU.sh --language es

French

./RUN_GPU.sh --language fr

German

./RUN_GPU.sh --language de

---

Available Ollama Models

You have these models installed:

• llama3.2:latest (2.0 GB) - Default - Fast and accurate
• llama3:8b (4.7 GB) - More powerful
• qwen2.5:3b (1.9 GB) - Fast alternative
• qwen2.5:7b (4.7 GB) - Powerful alternative
• qwen2.5:0.5b (397 MB) - Very fast, less accurate

To use a different model:

./RUN_DUTCH_LLM.sh --llm-model "llama3:8b"

---

Tips

Better Accuracy

Use larger Whisper model (slower):

./RUN_DUTCH.sh --model medium  # or: large

Faster Processing

Use smaller model or reduce interval:

./RUN_DUTCH.sh --model tiny --interval 3

Debug LLM Issues

./RUN_DUTCH_LLM.sh --llm-debug

---

Controls

• Ctrl+C to stop transcription
• Speak clearly into your microphone
• Wait ~5 seconds for transcription to appear
• Sentences appear with 📝 emoji