The highest tagged major version is
README
¶
Porcupine Wake Word Engine
Made in Vancouver, Canada by Picovoice
Porcupine is a highly-accurate and lightweight wake word engine. It enables building always-listening voice-enabled applications. It is
- using deep neural networks trained in real-world environments.
- compact and computationally-efficient. It is perfect for IoT.
- cross-platform. Raspberry Pi, BeagleBone, Android, iOS, Linux (x86_64), macOS (x86_64), Windows (x86_64), and web browsers are supported. Additionally, enterprise customers have access to ARM Cortex-M SDK.
- scalable. It can detect multiple always-listening voice commands with no added runtime footprint.
- self-service. Developers can train custom wake word models using Picovoice Console.
Compatibility
- Go 1.16+
- Runs on Linux (x86_64), macOS (x86_64) and Windows (x86_64)
Installation
go get github.com/Picovoice/porcupine/binding/go
Usage
To create an instance of the engine you first creat a Porcupine struct with the configuration parameters for the wake word engine and then make a call to .Init().
import . "github.com/Picovoice/porcupine/binding/go"
porcupine := Porcupine{BuiltInKeywords: []BuiltInKeyword{PICOVOICE}}
err := porcupine.Init()
if err != nil {
// handle init fail
}
In the above example, we've initialzed the engine to detect the built-in wake word "Picovoice". Built-in keywords are constants in the package with the BuiltInKeyword type.
Porcupine can detect multiple keywords concurrently
porcupine := Porcupine{BuiltInKeywords: []BuiltInKeyword{PICOVOICE, BUMBLEBEE}}
err := porcupine.Init()
To detect non-default keywords, use KeywordPaths parameter instead
porcupine := Porcupine{KeywordPaths: []string{"/path/to/keyword.ppn"}}
err := porcupine.Init()
The sensitivity of the engine can be tuned per keyword using the sensitivities parameter
porcupine := Porcupine{
BuiltInKeywords: []BuiltInKeyword{PICOVOICE, BUMBLEBEE}
Sensitivities: []float32{0.4, 0.9}}
err := porcupine.Init()
Sensitivity is the parameter that enables trading miss rate for the false alarm rate. It is a floating point number within [0, 1]. A higher sensitivity reduces the miss rate at the cost of increased false alarm rate.
When initialized, the valid sample rate is given by SampleRate. Expected frame length (number of audio samples in an input array) is given by FrameLength. The engine accepts 16-bit linearly-encoded PCM and operates on single-channel audio.
To feed audio into Porcupine, use the Process function in your capture loop. You must call Init() before calling Process.
func getNextFrameAudio() []int16{
// get audio frame
}
for {
keywordIndex, err := porcupine.Process(getNextFrameAudio())
if keywordIndex >= 0 {
// wake word detected!
}
}
When done resources have to be released explicitly.
porcupine.Delete()
Using a defer call to Delete() after Init() is also a good way to ensure cleanup.
Non-English Wake Words
In order to detect non-English wake words you need to use the corresponding model file. The model files for all supported languages are available here.
Demos
Check out the Porcupine Go demos here
Documentation
¶
Index ¶
Constants ¶
This section is empty.
Variables ¶
var ( // Number of audio samples per frame. FrameLength = nativePorcupine.nativeFrameLength() // Audio sample rate accepted by Picovoice. SampleRate = nativePorcupine.nativeSampleRate() // Porcupine version Version = nativePorcupine.nativeVersion() )
var BuiltInKeywords = []BuiltInKeyword{ ALEXA, AMERICANO, BLUEBERRY, BUMBLEBEE, COMPUTER, GRAPEFRUIT, GRASSHOPPER, HEY_GOOGLE, HEY_SIRI, JARVIS, OK_GOOGLE, PICOVOICE, PORCUPINE, TERMINATOR, }
List of available built-in wake words
Functions ¶
This section is empty.
Types ¶
type BuiltInKeyword ¶
type BuiltInKeyword string
BuiltInKeyword Type
const ( ALEXA BuiltInKeyword = "alexa" AMERICANO BuiltInKeyword = "americano" BLUEBERRY BuiltInKeyword = "blueberry" BUMBLEBEE BuiltInKeyword = "bumblebee" COMPUTER BuiltInKeyword = "computer" GRAPEFRUIT BuiltInKeyword = "grapefruit" GRASSHOPPER BuiltInKeyword = "grasshopper" HEY_GOOGLE BuiltInKeyword = "hey google" HEY_SIRI BuiltInKeyword = "hey siri" JARVIS BuiltInKeyword = "jarvis" OK_GOOGLE BuiltInKeyword = "ok google" PICOVOICE BuiltInKeyword = "picovoice" PORCUPINE BuiltInKeyword = "porcupine" TERMINATOR BuiltInKeyword = "terminator" )
Available built-in wake words constants
func (BuiltInKeyword) IsValid ¶
func (k BuiltInKeyword) IsValid() bool
Checks if a given BuiltInKeyword is valid
type Porcupine ¶
type Porcupine struct {
// Absolute path to the file containing model parameters.
ModelPath string
// Sensitivity values for detecting keywords. Each value should be a number within [0, 1]. A
// higher sensitivity results in fewer misses at the cost of increasing the false alarm rate.
Sensitivities []float32
// List of built-in keywords to use.
BuiltInKeywords []BuiltInKeyword
// Absolute paths to keyword model files.
KeywordPaths []string
// contains filtered or unexported fields
}
Porcupine struct
func (*Porcupine) Process ¶
Processes a frame of the incoming audio stream and emits the detection result. Frame of audio The number of samples per frame can be attained by calling `.FrameLength`. The incoming audio needs to have a sample rate equal to `.Sample` and be 16-bit linearly-encoded. Porcupine operates on single-channel audio. Returns a 0 based index if keyword was detected in frame. Returns -1 if no detection was made.
Source Files