schihei
f00f29ab6b
- Created directory structure for prompts (system and user prompts) - Added specialized prompts for lectures, meetings, and interviews - Updated enhancer.py to load prompts from files - Added --prompt-type CLI parameter to select prompt type - Updated documentation and enhancement proposals
2.9 KiB
2.9 KiB
mknotes
A command-line tool to transcribe all MP3, M4A, and WAV audio files in a directory using Faster Whisper, then enhance the transcriptions into comprehensive notes using OpenAI's GPT-4.1 model.
Features
- Batch transcribes all
.mp3,.m4a, and.wavfiles in a specified directory - Automatically converts WAV files to MP3 format before processing
- Converted MP3 files are saved in the same directory as the original WAV files
- Reuses existing MP3 files if they've already been converted
- Saves transcriptions as
.txtfiles - Enhances notes using GPT-4.1 with a custom prompt
- Outputs enhanced notes in markdown format
- Configurable input and output directories
Installation
# Clone the repository
git clone https://github.com/yourusername/mknotes.git
cd mknotes
# Create a virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
# Install ffmpeg (required for WAV to MP3 conversion)
# On Ubuntu/Debian:
# sudo apt-get install ffmpeg
# On macOS with Homebrew:
# brew install ffmpeg
# On Windows:
# Download from https://ffmpeg.org/download.html and add to PATH
Usage
export OPENAI_API_KEY="your-api-key-here"
python main.py --input-dir /path/to/audio/files --output-dir /path/to/output [--turbo]
--input-dir: Directory containing audio files (.mp3, .m4a, .wav) (required)--output-dir: Directory for output files (default: "output")--turbo: Enable turbo mode for faster inference (uses int8_float16 compute type)--force: Force re-processing of files even if output files already exist--prompt-type: Type of content to enhance (choices: "lecture", "meeting", "interview", default: "lecture")
Turbo Mode Hardware Requirements
The --turbo flag enables faster inference using the int8_float16 compute type, which can significantly speed up transcription. However, this requires:
- CUDA-compatible GPU with Tensor Cores (NVIDIA Ampere, Turing, or newer architecture)
- Or CPU with AVX2 support
If your hardware does not support this optimization, the program will automatically fall back to the next most compatible compute type and print a warning.
Compute Type Fallback
The program will attempt to use the most efficient compute type supported by your hardware, in the following order:
int8_float16(if--turbois enabled)float16int8float32(most compatible, works on virtually all hardware)
If a compute type is not supported, the program will try the next one in the list until successful.
Requirements
- Python 3.8+
- Faster Whisper
- OpenAI Python SDK
- pydub (for WAV to MP3 conversion)
- ffmpeg (required by pydub for audio conversion)