I'm attempting to solve this problem: SFSpeechRecognizer - detect end of utterance
The problem is that SFSpeechRecognizer callback fires every time the detected speech string changes, but it only fires after 60 seconds of silence (whereupon it sets the isFinal flag).
The suggested technique is to start a 2 second timer each time to callback fires, first invalidating the timer if it is already set.
I have implemented this technique. However at my timer callback is never getting hit.
Can anyone tell me why?
import Foundation
import Speech
@objc
public class Dictation : NSObject, SFSpeechRecognizerDelegate
{
@objc static let notification_finalText = Notification.Name("speech_gotFinalText")
@objc static let notification_interimText = Notification.Name("speech_textDidChange")
private let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-UK"))!
var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
private var recognitionTask: SFSpeechRecognitionTask?
let audioEngine = AVAudioEngine()
@objc var text_tmp : String? = ""
@objc var text_final : String? = ""
var timer : Timer?
override init()
{
super.init()
speechRecognizer.delegate = self
SFSpeechRecognizer.requestAuthorization { authStatus in
if authStatus != .authorized {
exit(0)
}
}
}
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
@objc
func tryStartRecording()
{
try! startRecording()
}
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
func startRecording() throws
{
text_final = ""
// Cancel the previous task if it's running.
if let recognitionTask = recognitionTask {
recognitionTask.cancel()
self.recognitionTask = nil
}
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
let inputNode = audioEngine.inputNode
/*
^ causes:
[plugin] AddInstanceForFactory: No factory registered for id <CFUUID 0x600000247200> F8BB1C28-BAE8-11D6-9C31-00039315CD46
HALC_ShellDriverPlugIn::Open: Can't get a pointer to the Open routine
HALC_ShellDriverPlugIn::Open: Can't get a pointer to the Open routine
*/
if inputNode.inputFormat(forBus: 0).sampleRate == 0 {
fatalError("Audio engine has no input node")
}
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to created a SFSpeechAudioBufferRecognitionRequest object")
}
// Configure request so that results are returned before audio recording is finished
recognitionRequest.shouldReportPartialResults = true
// A recognition task represents a speech recognition session.
// We keep a reference to the task so that it can be cancelled.
recognitionTask = speechRecognizer.recognitionTask( with: recognitionRequest )
{ result, error in
self.timer?.invalidate()
print( "New Timer" )
self.timer = Timer(timeInterval:2.0, repeats:false) { _ in
print( "*** Timer Callback -- NEVER HITS! ***" )
self.timer?.invalidate()
self.text_final = result!.bestTranscription.formattedString
NotificationCenter.default.post( name: Dictation.notification_finalText, object: nil )
self.stopRecording()
}
var isFinal = false
if let result = result {
isFinal = result.isFinal
if isFinal {
self.text_final = result.bestTranscription.formattedString
} else {
self.text_tmp = result.bestTranscription.formattedString
}
let notification = isFinal ? Dictation.notification_finalText : Dictation.notification_interimText
NotificationCenter.default.post( name: notification, object: nil )
}
if error != nil || isFinal {
self.audioEngine.stop()
inputNode.removeTap( onBus: 0 )
self.recognitionRequest = nil
self.recognitionTask = nil
}
}
let recordingFormat = inputNode.outputFormat(forBus: 0)
inputNode.installTap( onBus: 0, bufferSize: 1024, format: recordingFormat )
{ (buffer: AVAudioPCMBuffer, when: AVAudioTime) in
self.recognitionRequest?.append( buffer )
}
audioEngine.prepare()
try audioEngine.start()
print( self.audioEngine.description )
}
// - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
@objc
func stopRecording()
{
audioEngine.stop()
recognitionRequest?.endAudio()
}
}