Files
verbatim-dicta/QUICK_START.md
2025-12-17 22:11:08 +01:00

106 lines
1.7 KiB
Markdown

# Quick Start Guide
## Dutch Language (Nederlands)
### Basic Dutch Transcription
```bash
./RUN_DUTCH.sh
```
- ✅ GPU-accelerated (RTX 4060 Ti)
- ✅ Sentence extraction (complete zinnen)
- ✅ Base model (goede balans snelheid/nauwkeurigheid)
### Dutch with LLM Analysis
```bash
./RUN_DUTCH_LLM.sh
```
- ✅ All features from basic version
- ✅ Fact-checking van uitspraken
- ✅ Automatische vraag generatie
- Uses llama3.2:latest model
### Save to File
```bash
./RUN_DUTCH.sh --output transcript.txt
./RUN_DUTCH_LLM.sh --output enriched.txt
```
---
## English Language
### Basic English Transcription
```bash
./RUN_GPU.sh
```
### English with LLM
```bash
./RUN_GPU.sh --enable-llm
```
---
## Other Languages
### Spanish
```bash
./RUN_GPU.sh --language es
```
### French
```bash
./RUN_GPU.sh --language fr
```
### German
```bash
./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:
```bash
./RUN_DUTCH_LLM.sh --llm-model "llama3:8b"
```
---
## Tips
### Better Accuracy
Use larger Whisper model (slower):
```bash
./RUN_DUTCH.sh --model medium # or: large
```
### Faster Processing
Use smaller model or reduce interval:
```bash
./RUN_DUTCH.sh --model tiny --interval 3
```
### Debug LLM Issues
```bash
./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