Nemo ASR Parakeet CTC 0.6B Pipeline Tuning
This example demonstrates how to use NVIDIA AITune to tune the Nemo ASR with Parakeet-CTC-0.6B model.
Environment Setup
You can use either of the following options to set up the environment:
Option 1 - virtual environment managed by you
Activate your virtual environment and install the dependencies:
Option 2 - virtual environment managed by uv
Install dependencies:
Usage
Sample audio file
The example uses a sample audio file that is downloaded automatically when you run the
commands below without an explicit --audio_path.
You can also download it manually:
Tuning and inference the model
To tune the ASR model, run:
To infer the ASR model, run:
Logging hardware metrics
If you would like to log hardware metrics during tuning or inference, export AITUNE_HARDWARE_METRICS=True environment variable, e.g.
AI Dynamo ParakeetCTC Deployment
To run ParakeetCTC as an AI Dynamo service, you need to first tune your model and then launch a test run using the provided script.
This script starts the frontend and backend services, waits for them to be ready, then runs a test client to send sample requests. Once the test completes, all services are automatically shut down. This is meant as a functional check, not to provide a permanent server.
Dynamic batching
The service uses dynamic batching — requests are grouped and processed together for efficiency. Currently, there is one frontend and one worker. To support multiple workers, move batching to a separate service that handles request grouping.
Model Details
Can be found in following pages: