I'm trying to write a speech recognizer that will have the ability to be cleared after some duration (like two seconds) without switching it off.
private func startRecording() throws {
recognitionTask?.cancel()
self.recognitionTask = nil
let audioSession = AVAudioSession.sharedInstance()
try audioSession.setCategory(.record, mode: .measurement, options: .duckOthers)
try audioSession.setActive(true, options: .notifyOthersOnDeactivation)
let inputNode = audioEngine.inputNode
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let recognitionRequest = recognitionRequest else { fatalError("Unable to create a SFSpeechAudioBufferRecognitionRequest object") }
recognitionRequest.shouldReportPartialResults = true
// Keep speech recognition data on device
if #available(iOS 13, *) {
recognitionRequest.requiresOnDeviceRecognition = false
}
recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { result, error in
var isFinal = false
if let result = result {
self.textView.text = result.bestTranscription.formattedString
// MARK: here after 2 seconds my recognition should clear it's own result in string
isFinal = result.isFinal
print("Text \(result.bestTranscription.formattedString)")
}
if error != nil || isFinal {
self.audioEngine.stop()
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
self.recordButton.isEnabled = true
self.recordButton.setTitle("Start Recording", for: [])
}
}
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()
textView.text = "(Go ahead, I'm listening)"
}
I can not rebuild speech recognition. It should be working constantly.
I tried to do the following, but afterwards my microphone turns off:
inputNode.removeTap(onBus: 0)
audioEngine.inputNode.removeTap(onBus: 0)
Related
We are creating an online book reading app in which we are initiating video call (group call:- for video call. we are using agora SDK) and at the join of call we start book reading and highlight words at other members' end also and recording/recognition text we are using SFSpeechRecognizer but whenever call kit start and video call start SFSpeechRecognizer start to record audio at others end it's getting failed always, can you please provide any solution to record audio during the video call.
//
// Speech.swift
// Edsoma
//
// Created by Kapil on 16/02/22.
//
import Foundation
import AVFoundation
import Speech
protocol SpeechRecognizerDelegate {
func didSpoke(speechRecognizer : SpeechRecognizer , word : String?)
}
class SpeechRecognizer: NSObject {
private let speechRecognizer = SFSpeechRecognizer(locale: Locale.init(identifier: "en-US")) //1
private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
private var recognitionTask: SFSpeechRecognitionTask?
private let audioEngine = AVAudioEngine()
var delegate : SpeechRecognizerDelegate?
static let shared = SpeechRecognizer()
var isOn = false
func setup(){
speechRecognizer?.delegate = self //3
SFSpeechRecognizer.requestAuthorization { (authStatus) in //4
var isButtonEnabled = false
switch authStatus { //5
case .authorized:
isButtonEnabled = true
case .denied:
isButtonEnabled = false
print("User denied access to speech recognition")
case .restricted:
isButtonEnabled = false
print("Speech recognition restricted on this device" )
case .notDetermined:
isButtonEnabled = false
print("Speech recognition not yet authorized")
#unknown default:
break;
}
OperationQueue.main.addOperation() {
// self.microphoneButton.isEnabled = isButtonEnabled
}
}
}
func transcribeAudio(url: URL) {
// create a new recognizer and point it at our audio
let recognizer = SFSpeechRecognizer()
let request = SFSpeechURLRecognitionRequest(url: url)
// start recognition!
recognizer?.recognitionTask(with: request) { [unowned self] (result, error) in
// abort if we didn't get any transcription back
guard let result = result else {
print("There was an error: \(error!)")
return
}
// if we got the final transcription back, print it
if result.isFinal {
// pull out the best transcription...
print(result.bestTranscription.formattedString)
}
}
}
func startRecording() {
isOn = true
let inputNode = audioEngine.inputNode
if recognitionTask != nil {
inputNode.removeTap(onBus: 0)
self.audioEngine.stop()
self.recognitionRequest = nil
self.recognitionTask = nil
DispatchQueue.main.asyncAfter(deadline: DispatchTime.now() + 1) {
self.startRecording()
}
return
debugPrint("****** recognitionTask != nil *************")
}
let audioSession = AVAudioSession.sharedInstance()
do {
try audioSession.setCategory(AVAudioSession.Category.multiRoute)
try audioSession.setMode(AVAudioSession.Mode.measurement)
try audioSession.setActive(true, options: .notifyOthersOnDeactivation)
} catch {
print("audioSession properties weren't set because of an error.")
}
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
}
recognitionRequest.shouldReportPartialResults = true
recognitionRequest.taskHint = .search
recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
var isFinal = false
if result != nil {
self.delegate?.didSpoke(speechRecognizer: self, word: result?.bestTranscription.formattedString)
debugPrint(result?.bestTranscription.formattedString)
isFinal = (result?.isFinal)!
}
if error != nil {
debugPrint("Speech Error ====>",error)
inputNode.removeTap(onBus: 0)
self.audioEngine.stop()
self.recognitionRequest = nil
self.recognitionTask = nil
if BookReadingSettings.isSTTEnable{
DispatchQueue.main.asyncAfter(deadline: DispatchTime.now() + 1) {
self.startRecording()
}
}
// self.microphoneButton.isEnabled = true
}
})
// let recordingFormat = AVAudioFormat.init(commonFormat: .pcmFormatFloat32, sampleRate: <#T##Double#>, interleaved: <#T##Bool#>, channelLayout: <#T##AVAudioChannelLayout#>)//inputNode.outputFormat(forBus: 0)
inputNode.removeTap(onBus: 0)
let sampleRate = AVAudioSession.sharedInstance().sampleRate
let recordingFormat = AVAudioFormat(standardFormatWithSampleRate: sampleRate, channels: 1)
inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
audioEngine.prepare()
do {
try audioEngine.start()
} catch {
print("audioEngine couldn't start because of an error.")
}
debugPrint("Say something, I'm listening!")
//textView.text = "Say something, I'm listening!"
}
/* func stopRecording(){
isOn = false
debugPrint("Recording stoped")
self.audioEngine.stop()
recognitionTask?.cancel()
let inputNode = audioEngine.inputNode
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
}*/
func stopRecording(){
isOn = false
debugPrint("Recording stoped")
let inputNode = audioEngine.inputNode
inputNode.removeTap(onBus: 0)
self.audioEngine.stop()
recognitionTask?.cancel()
self.recognitionRequest = nil
self.recognitionTask = nil
}
}
In one of my application I am using the Speech framework for converting user's voice into Text.
Basically I want my application hands-free with some commands It can operate.
So there is a limit of Apple that has only 1000 request per hour and SFSpeechRecognitionTask only last about 1 minute only.
I want SFSpeechRecognitionTask should make alive and keep recognise the voice.
So what is the best way we can do with the code. Is it too much battery gain If I will do restart SFSpeechRecognitionTask in every 1 min?
I have done code like below to start detecting voice and it's going to stop after 1 minute.
Please help me out if there will be a way to achieve it.
func startRecording() {
if recognitionTask != nil {
recognitionTask?.cancel()
recognitionTask = nil
}
let audioSession = AVAudioSession.sharedInstance()
do {
try audioSession.setCategory(AVAudioSessionCategoryRecord)
try audioSession.setMode(AVAudioSessionModeMeasurement)
try audioSession.setActive(true, with: .notifyOthersOnDeactivation)
} catch {
print("audioSession properties weren't set because of an error.")
}
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let inputNode = audioEngine.inputNode else {
fatalError("Audio engine has no input node")
}
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
}
recognitionRequest.shouldReportPartialResults = true
recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
var isFinal = false
if result != nil {
if self.speechTimer != nil
{
if (self.speechTimer?.isValid)!
{
self.speechTimer?.invalidate()
}
self.speechTimer = nil;
}
print(result?.bestTranscription.formattedString as Any)
self.speechTimer = Timer.scheduledTimer(withTimeInterval: 2.0, repeats: false, block: { (timer) in
print("Recognition task restart")
})
isFinal = (result?.isFinal)!
if isFinal {
print("Final String: \(result?.bestTranscription.formattedString ?? "No string")")
}
}
})
let recordingFormat = inputNode.outputFormat(forBus: 0)
inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
audioEngine.prepare()
do {
try audioEngine.start()
} catch {
print("audioEngine couldn't start because of an error.")
}
}
Video not playing after SpeechRecognizer. Not getting any error just stuck on AVPlayerViewController. I have stopped speechRecognizer also. then after I am trying to play video. The video perfectly plays before speechRecognizer.
Maybe that possible speechRecognizer is not stopping by this code. So, Maybe the problem is in stopRecording().
#IBAction func btnRecord(_ sender: Any) {
player.pause()
player.seek(to: CMTime.init(value: 0, timescale: player.currentTime().timescale))
if self.audioEngine.isRunning {
self.audioEngine.stop()
self.recognitionRequest?.endAudio()
}
else {
try! self.startRecording()
}
}
private func startRecording() throws {
// Cancel the previous task if it's running.
if let recognitionTask = recognitionTask {
recognitionTask.cancel()
self.recognitionTask = nil
}
let audioSession = AVAudioSession.sharedInstance()
try audioSession.setCategory(AVAudioSession.Category.record, mode: .default, options: [])
try audioSession.setMode(AVAudioSession.Mode.measurement)
try audioSession.setActive(true, options: .notifyOthersOnDeactivation)
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
let inputNode = audioEngine.inputNode
//else { 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
var isFinal = false
if let result = result {
self.text = result.bestTranscription.formattedString
self.lblText.text = self.text
isFinal = result.isFinal
}
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()
}
private func stopRecording() {
audioEngine.stop()
recognitionRequest?.endAudio()
if let recognitionTask = recognitionTask {
recognitionTask.cancel()
self.recognitionTask = nil
}
}
#IBAction func btnDonePopup(_ sender: Any) {
self.stopRecording()
self.playVideo()
}
Please change audioSession.setCategory to default value:
if error != nil || isFinal {
self.audioEngine.stop()
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
do {
try audioSession.setCategory(.soloAmbient, mode: .measurement, options: [])
} catch { }
}
I am working on an app that uses the new Speech framework in ios 10 to do some speech-to-text stuff. What is the best way of stopping the recognition when the user stops talking?
private func startRecording() {
isRecording = true
if let recognitionTask = recognitionTask {
recognitionTask.cancel()
self.recognitionTask = nil
}
let audioSession = AVAudioSession.sharedInstance()
do {
try audioSession.setCategory(AVAudioSessionCategoryRecord, mode: AVAudioSessionModeMeasurement)
try audioSession.setActive(true, with: .notifyOthersOnDeactivation)
} catch {
print("audioSession properties weren't set because of an error.")
return
}
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let inputNode = audioEngine.inputNode else {
fatalError("Audio engine has no input node")
}
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
}
recognitionRequest.shouldReportPartialResults = true
recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
if let result = result {
if error != nil || result.isFinal {
self.audioEngine.stop()
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
let questionText = result.bestTranscription.formattedString
isRecording = false
self.audioEngine.stop()
recognitionRequest.endAudio()
self.audioEngine.inputNode?.removeTap(onBus: 0)
}
}
})
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()
}
I want this code to be called once user does not talk
private func stopRecording() {
isRecording = false
audioEngine.stop()
recognitionRequest?.endAudio()
audioEngine.inputNode?.removeTap(onBus: 0)
}
I am making an application that does Text-to-speech and speech-to-text.
The problem i am having right now is that text-to-speech works fine using AVSpeechSynthesizer. But after i record and do speech-to-text using SFSpeechRecognizer, the text-to-speech stops working (ie, doesn't talk back).
I am new to swift too. But i got this code from a couple of different tutorials and tried to merge them together.
Here's my code:
private var speechRecognizer = SFSpeechRecognizer(locale: Locale.init(identifier: "en-US"))!
private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
private var recognitionTask: SFSpeechRecognitionTask?
private var audioEngine = AVAudioEngine()
#objc(speak:location:date:callback:)
func speak(name: String, location: String, date: NSNumber,_ callback: #escaping (NSObject) -> ()) -> Void {
let utterance = AVSpeechUtterance(string: name)
let synthesizer = AVSpeechSynthesizer()
synthesizer.speak(utterance)
}
#available(iOS 10.0, *)
#objc(startListening:location:date:callback:)
func startListening(name: String, location: String, date: NSNumber,_ callback: #escaping (NSObject) -> ()) -> Void {
if audioEngine.isRunning {
audioEngine.stop()
recognitionRequest?.endAudio()
} else {
if recognitionTask != nil { //1
recognitionTask?.cancel()
recognitionTask = nil
}
let audioSession = AVAudioSession.sharedInstance() //2
do {
try audioSession.setCategory(AVAudioSessionCategoryPlayAndRecord)
try audioSession.setMode(AVAudioSessionModeMeasurement)
try audioSession.setActive(true, with: .notifyOthersOnDeactivation)
} catch {
print("audioSession properties weren't set because of an error.")
}
recognitionRequest = SFSpeechAudioBufferRecognitionRequest() //3
guard let inputNode = audioEngine.inputNode else {
fatalError("Audio engine has no input node")
} //4
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
} //5
recognitionRequest.shouldReportPartialResults = true //6
recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in //7
var isFinal = false //8
if result != nil {
print(result?.bestTranscription.formattedString) //9
isFinal = (result?.isFinal)!
}
if error != nil || isFinal { //10
self.audioEngine.stop()
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
}
})
let recordingFormat = inputNode.outputFormat(forBus: 0) //11
inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
audioEngine.prepare() //12
do {
try audioEngine.start()
} catch {
print("audioEngine couldn't start because of an error.")
}
}
}
They both have an AVAudioSession.
For AVSpeechSynthesizer I suppose it has to be set to:
_audioSession.SetCategory(AVAudioSessionCategory.Playback,
AVAudioSessionCategoryOptions.MixWithOthers);
and For SFSpeechRecognizer:
_audioSession.SetCategory(AVAudioSessionCategory.PlayAndRecord,
AVAudioSessionCategoryOptions.MixWithOthers);
Hope it helps.