Running Inference
Verify Server Health
Perform a health check on the gRPC endpoint.
-
Install
grpcurlfrom the fullstorydev/grpcurl repo.Example commands to run on Ubuntu:
-
Download the health checking proto:
-
Run the health check on
<server_ip>or localhost:If the service is ready, you get a response similar to the following:
To use grpcurl with an SSL enabled server, avoid using the --plaintext argument. Instead, use --cacert with a CA certificate, --key with a private key, or --cert with a certificate file. For more details, refer to grpcurl --help.
Running Inference via Script
1. Clone the Repository
Download the BNR Python client code by cloning the NVIDIA Maxine NIM Clients repository:
2. Install Dependencies
3. Run the Python Client
You can use the sample client script in the BNR GitHub repo to send a gRPC request to the hosted NIM server:
-
Go to the scripts directory.
-
Run the command to send the gRPC request.
Streaming mode (recommended): The following example command streams the raw audio data from the sample audio file in 10 ms chunks and saves streamed output from the NIM to bnr_48k_output.wav file in the current folder.
Ensure that the selected --sample-rate aligns with the NIM_MODEL_PROFILE model type configuration to maintain compatibility.
Transactional mode: The following example command processes the packaged sample audio file and generates a bnr_48k_output.wav file in the current folder.
To use the client in Streaming mode, launch the NIM in Streaming mode. Similarly, to use the client in Transactional mode, launch the NIM in Transactional mode.
Only WAV files are supported.
Please note that the first inference isn’t indicative of the model’s performance.
For more details on modes, refer to Overview.
Usage for Preview API Request
The Preview API provides a hosted version of BNR, which can be used for testing.
To use the hosted version of the API, use the following command:
For further details, refer to the Try API documentation.
Command-Line Arguments
To view the details of command-line arguments, run this command:
--target <ip:port>- URI of NIM’s gRPC service. Usegrpc.nvcf.nvidia.com:443when hosted on NVCF. Default value is127.0.0.1:8001.--preview-mode- Flag to send request to preview NVCF server on Try API.--ssl-mode- Set the SSL mode toTLSorMTLS. Defaults to no SSL. When running preview, TLS mode must be used with the default root certificate.--ssl-key- The path to client’s PEM encoded private key. Only required for MTLS mode.--ssl-cert- The path to client’s PEM encoded public certificate. Only required for MTLS mode.--ssl-root-cert- The path to PEM encoded root certificate. Used only for TLS or MTLS modes.--api-key <NGC_API_KEY>- NGC API key required for authentication. Utilized when using TRY API, ignored otherwise.--function-id- NVCF function ID for the service. Utilized when using TRY API, ignored otherwise.--input- The path to the input audio file. Default value is../assets/bnr_48k_input.wav.--output- The path for the output audio file. Default is./bnr_48k_output.wav.--streaming- Flag to control whether streaming or transactional mode should be used. The default is streaming mode; to enable transactional mode, set to False.--sample-rate- Sample rate of input audio file in Hz. It can be set to48000or16000. Default value is48000.--intensity-ratio- Intensity ratio value between 0 and 1 to control denoising intensity. Default is 1.0 (maximum denoising).
Python Notebook
For an interactive experience and to explore all feature parameters, we provide a comprehensive Python notebook that demonstrates the Background Noise Removal service capabilities.
The Python notebook is located at notebook/ in the bnr client folder.