Audio processing and note-taking application with AI transcription.

This project uses uv for dependency management.

1. Install uv if you haven't already:

   curl -LsSf https://astral.sh/uv/install.sh | sh

2. Install dependencies:

   # Install core dependencies
   uv sync --no-install-project
   
   # Install with optional LLM dependencies
   uv sync --no-install-project --extra llm

Use uv run to execute Python scripts with the project environment:

# Run the main note taker
uv run python note_taker.py

# Run LLM tests
uv run python llm_test.py
uv run python llm_test_2.py

Core dependencies:

• transformers - Hugging Face transformers library
• torch - PyTorch for machine learning
• sounddevice - Audio recording/playback
• soundfile - Audio file I/O
• scipy - Scientific computing
• numpy - Numerical computing
• silero-vad - Voice activity detection
• fire - Command-line interface generation

Optional LLM dependencies (--extra llm):

• accelerate - Hugging Face accelerate for faster training/inference
• bitsandbytes - Memory efficient optimizers (Linux only)
• sentencepiece - Tokenization library