Rhino Speech-to-Intent
Rust Quick Start

Platforms

• Linux (x86_64)
• macOS (x86_64, arm64)
• Windows (x86_64)
• Raspberry Pi (Zero, 3, 4, 5)

Requirements

• Picovoice Account & AccessKey
• Rust 1.54+
• Cargo

Picovoice Account & AccessKey

Signup or Login to Picovoice Console to get your AccessKey. Make sure to keep your AccessKey secret.

Quick Start

Setup

1. Download and install Rust.

2. Add pv_rhino to the Cargo.toml manifest:

[dependencies]
pv_rhino = "*"

Usage

Create an instance of Rhino Speech-to-Intent using either a pre-built context file (.rhn) from the Rhino GitHub Repository or a custom context created with the Picovoice Console:

use rhino::{Rhino, RhinoBuilder};

let rhino: Rhino = RhinoBuilder::new(
    "${ACCESS_KEY}",
    "${CONTEXT_FILE_PATH}",
)
.init()
.expect("Unable to create Rhino");

Pass in frames of audio to the .process function:

fn next_audio_frame() -> Vec<i16> {
    // ..
}

loop {
    let audio_frame: Vec<i16> = next_audio_frame();
    if let Ok(is_finalized) = rhino.process(&audio_frame) {
        if is_finalized {
            if let Ok(inference) = rhino.get_inference() {
                if inference.is_understood {
                    let intent = inference.intent.unwrap();
                    let slots = inference.slots;
                    // take action based on inferred intent and slot values
                } else {
                    // handle unsupported commands
                }
            }
        }
    }
}

Custom Contexts

Create custom context files using the Picovoice Console. Download the custom context file (.rhn) and pass it into the RhinoBuilder constructor.

Non-English Languages

Use the corresponding model file (.pv) to process non-English contexts. The model files for all supported languages are available on the Rhino Speech-to-Intent GitHub repository.

Pass in the model file using the model_path builder method to change the detection language:

let rhino: Rhino = RhinoBuilder::new(
    "${ACCESS_KEY}",
    "${CONTEXT_FILE_PATH}",
)
.model_path("${MODEL_FILE_PATH}")
.init()
.expect("Unable to create Rhino");

Demo

For the Rhino Speech-to-Intent Rust SDK, we offer demo applications that demonstrate how to use the Speech-to-Intent engine on real-time audio streams (i.e. microphone input) and audio files.

Setup

Clone the Rhino Speech-to-Intent GitHub Repository:

git clone --recurse-submodules https://github.com/Picovoice/rhino.git

Usage

Use the --help flag to see the usage options for the demo:

cd rhino/demo/rust/micdemo
cargo run --release -- --help

Ensure you have a working microphone connected to your system and run the following command to make inferences based on the given context file:

cargo run --release -- --access_key "${ACCESS_KEY}" --context_path "${CONTEXT_FILE_PATH}"

For more information on our Rhino Speech-to-Intent demos for Rust, head over to our GitHub repository.

Resources