ios - 识别语音到文本 Swift
问题描述
是否可以识别语音,然后使用自定义键盘将其转换为文本。就像 iphone 中的默认消息应用程序一样。
截屏
1. iphone键盘默认识别语音。
2. 语音转文字
任何帮助将不胜感激。
提前致谢。
解决方案
我有以下代码在我的示例应用程序中用于将语音转换为文本。
import UIKit
import Speech
import AVKit
class ViewController: UIViewController {
//------------------------------------------------------------------------------
// MARK:-
// MARK:- Outlets
//------------------------------------------------------------------------------
@IBOutlet weak var btnStart : UIButton!
@IBOutlet weak var lblText : UILabel!
//------------------------------------------------------------------------------
// MARK:-
// MARK:- Variables
//------------------------------------------------------------------------------
let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))
var recognitionRequest : SFSpeechAudioBufferRecognitionRequest?
var recognitionTask : SFSpeechRecognitionTask?
let audioEngine = AVAudioEngine()
//------------------------------------------------------------------------------
// MARK:-
// MARK:- Action Methods
//------------------------------------------------------------------------------
@IBAction func btnStartSpeechToText(_ sender: UIButton) {
if audioEngine.isRunning {
self.audioEngine.stop()
self.recognitionRequest?.endAudio()
self.btnStart.isEnabled = false
self.btnStart.setTitle("Start Recording", for: .normal)
} else {
self.startRecording()
self.btnStart.setTitle("Stop Recording", for: .normal)
}
}
//------------------------------------------------------------------------------
// MARK:-
// MARK:- Custom Methods
//------------------------------------------------------------------------------
func setupSpeech() {
self.btnStart.isEnabled = false
self.speechRecognizer?.delegate = self
SFSpeechRecognizer.requestAuthorization { (authStatus) in
var isButtonEnabled = false
switch authStatus {
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")
}
OperationQueue.main.addOperation() {
self.btnStart.isEnabled = isButtonEnabled
}
}
}
//------------------------------------------------------------------------------
func startRecording() {
// Clear all previous session data and cancel task
if recognitionTask != nil {
recognitionTask?.cancel()
recognitionTask = nil
}
// Create instance of audio session to record voice
let audioSession = AVAudioSession.sharedInstance()
do {
try audioSession.setCategory(AVAudioSession.Category.record, mode: AVAudioSession.Mode.measurement, options: AVAudioSession.CategoryOptions.defaultToSpeaker)
try audioSession.setActive(true, options: .notifyOthersOnDeactivation)
} catch {
print("audioSession properties weren't set because of an error.")
}
self.recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
let inputNode = audioEngine.inputNode
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
}
recognitionRequest.shouldReportPartialResults = true
self.recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
var isFinal = false
if result != nil {
self.lblText.text = result?.bestTranscription.formattedString
isFinal = (result?.isFinal)!
}
if error != nil || isFinal {
self.audioEngine.stop()
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
self.btnStart.isEnabled = true
}
})
let recordingFormat = inputNode.outputFormat(forBus: 0)
inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
self.audioEngine.prepare()
do {
try self.audioEngine.start()
} catch {
print("audioEngine couldn't start because of an error.")
}
self.lblText.text = "Say something, I'm listening!"
}
//------------------------------------------------------------------------------
// MARK:-
// MARK:- View Life Cycle Methods
//------------------------------------------------------------------------------
override func viewDidLoad() {
super.viewDidLoad()
self.setupSpeech()
}
}
//------------------------------------------------------------------------------
// MARK:-
// MARK:- SFSpeechRecognizerDelegate Methods
//------------------------------------------------------------------------------
extension ViewController: SFSpeechRecognizerDelegate {
func speechRecognizer(_ speechRecognizer: SFSpeechRecognizer, availabilityDidChange available: Bool) {
if available {
self.btnStart.isEnabled = true
} else {
self.btnStart.isEnabled = false
}
}
}
我为上面的 ViewController 的 UI 附上了以下屏幕截图。
推荐阅读
- javascript - 在 JavaScript 平台游戏中为玩家选择 x 和 y 坐标
- ios - Cordova 9 ios 5.1.1 - 从存储中播放视频
- c++ - 交点 Point1.Y 和 Y 应该相等。但是 Point1.Y 和 Y 是有区别的。为什么?
- python - 如何将numpy数组转换为压缩格式进行传输?
- angular - Angular 10 CORE 阻止了我对本地 ms 的休息呼叫
- python - 迷失在 Sympy 解决方案中
- php - 如何在 Cakephp 3.9 中加载 Google SDK
- spring - Spring Boot - 将 Next 和 Prev 链接添加到控制器响应
- r - 自己的包中的隐形功能描述
- reactjs - 如何根据反应中其他graphql的响应调用graphql?