Parakeet Managed Inference Job configuration
Fields you set when you create a Parakeet Managed Inference Job.
A Parakeet Managed Inference Job takes the following fields, as well as the common fields and GPU configuration that every job takes.
| Field | Required | CLI flag | Description |
|---|---|---|---|
| Model | Yes | --model | The Parakeet model to serve, nvidia/parakeet-tdt-0.6b-v3. |
| Endpoint name | Yes | --endpoint-name | The name of the transcription endpoint, which forms a path segment in its URL. The name has 3 to 63 characters, and uses only lowercase letters, digits, and hyphens. It must be unique across every Managed Inference Job in the deployment, including failed jobs that you haven't deleted. |
| Chunk duration | No | --chunk-duration | The audio chunk length, in seconds. The minimum is 10, which the CLI also sends when you omit the flag. |
| Chunk overlap | No | --chunk-overlap | The overlap between chunks, in seconds. The value must be less than the chunk duration. The minimum is 5, which the CLI also sends when you omit the flag. |
| Max file size | No | --max-file-size-mb | The maximum upload size, in MB. The minimum is 1024, which the CLI also sends when you omit the flag. |
| Replicas | No | --replica | The number of endpoint replicas. One of 1, 2, or 4. |
| Require Authorization header | No | --require-auth-header / --no-auth-header | Whether callers must send an authorization header. true or false. |
A Parakeet job also reads environment variables from its model master. See Parakeet server settings.