iOS（Swift）语音转录 - 连续转录期间捕获最后一个字/数字

Question

我正在为正在进行的语音应用程序而苦苦挣扎。我遵循了Dev示例，以在Apple的开发人员网站上创建语音识别器

但是，我的应用想法要求我在说话时以一系列数字捕获每个数字。有了以下代码，我可以成功地说一系列数字（例如“ 2、5、3、7、10、6 ...”），一旦我停止，它最终将返回一个sftranscription数组我说的数字。我最终之所以说，是因为语音识别器一直在不断尝试以人类语言或格式确定可理解的响应（在这种情况下，是电话号码，较大的多位数数字等），这是对听写和人类语言。但是我想让每个单词（数字）在尝试理解它之前所说的那样。是否有一种方法可以在识别器尝试将其与所有其他单词之前的识别器尝试之前抓住最后一句话？

import UIKit
import Speech

public class ViewController: UIViewController, SFSpeechRecognizerDelegate {
      
    private let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))!
    private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
    private var recognitionTask: SFSpeechRecognitionTask?
    private let audioEngine = AVAudioEngine()
    @IBOutlet var textView: UITextView!
    @IBOutlet var recordButton: UIButton!
    
    private var isListening = false
    
    public override func viewDidLoad() {
        super.viewDidLoad()
            recordButton.isEnabled = false
        textView.isEditable = false
    }
    
    override public func viewDidAppear(_ animated: Bool) {
        super.viewDidAppear(animated)
        speechRecognizer.delegate = self
        SFSpeechRecognizer.requestAuthorization { authStatus in
            OperationQueue.main.addOperation {
                switch authStatus {
                case .authorized:
                    self.recordButton.isEnabled = true
                case .denied:
                    self.recordButton.isEnabled = false
                    self.recordButton.setTitle("User denied access to speech recognition", for: .disabled)
                case .restricted:
                    self.recordButton.isEnabled = false
                    self.recordButton.setTitle("Speech recognition restricted on this device", for: .disabled)
                case .notDetermined:
                    self.recordButton.isEnabled = false
                    self.recordButton.setTitle("Speech recognition not yet authorized", for: .disabled)
                default:
                    self.recordButton.isEnabled = false
                }
            }
        }
    }
    
    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
        if #available(iOS 13, *) {
            recognitionRequest.requiresOnDeviceRecognition = false
        }
        recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { result, error in
            var isFinal = false
            if let result = result {
                
                if self.isListening {
                    result.transcriptions.forEach { transcription in  // Grab SFTranscription from result
                        transcription.segments.forEach { segment in
                            print( segment.substring )
                        }
                    }
                    print("---")
                }

                isFinal = result.isFinal
            }
            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)"
    }
    public func speechRecognizer(_ speechRecognizer: SFSpeechRecognizer, availabilityDidChange available: Bool) {
        if available {
            recordButton.isEnabled = true
            recordButton.setTitle("Start Recording", for: [])
        } else {
            recordButton.isEnabled = false
            recordButton.setTitle("Recognition Not Available", for: .disabled)
        }
    }
    @IBAction func recordButtonTapped() {
        if audioEngine.isRunning {
            audioEngine.stop()
            recognitionRequest?.endAudio()
            recordButton.isEnabled = false
            recordButton.setTitle("Stopping", for: .disabled)
            self.isListening = false
        } else {
            do {
                try startRecording()
                recordButton.setTitle("Stop Recording", for: [])
                self.isListening = true
            } catch {
                recordButton.setTitle("Recording Not Available", for: [])
            }
        }
    }
}

说“ 4、7、5、5、4、3” - “ ---”之后的每个块表示“ 4、7、5、5、4、3”的示例输出表示一个返回的成绩单中的所有段。

For
---
For
seven
---
47
---
475
---
4
7
5
---
4755
---
47554
---
475543
---
475543
---
4
7
5
5
4
3

我可以很容易地通过功能轻松地处理拼写的响应（例如，“对于“ 4”），但是长串联的字符串编号是使我陷入困境。我想在它们加入之前抓住它们，而不必等到结束，最终将它们分为单个细分市场。

感谢您的帮助！