This project provides a simple command-line interface (CLI) for running audio inference, testing a model, or launching a Flask server.
- Run inference on a single audio file
- Batch test the model on a directory of audio files
- Launch a Flask API server
- Clone the repository:
git clone <your-repo-url>
cd <your-repo-folder>- Install dependencies:
pip install -r requirements.txtRun the CLI using:
python src/cli.py [OPTIONS]| Option | Description |
|---|---|
--infer |
Path to a single audio file for inference |
--test |
Run model tests on a folder of audio files |
--audio_location |
Path to folder containing audio files (required with --test) |
--server |
Launch the Flask server |
python src/cli.py --infer path/to/audio.wavpython src/cli.py --test --audio_location path/to/audio_folder- Validates the folder path
- Sets
AUDIO_LOCATIONas an environment variable - Executes:
python src/model_test.py--audio_location is required when using --test.
python src/cli.py --server- Starts the Flask server by running:
python src/flask_server.py