7. Vision, Natural Language, dan Speech

// vision: OCR — extract text dari image
import Vision

let request = VNRecognizeTextRequest { request, error in
    guard let observations = request.results as? [VNRecognizedTextObservation] else { return }
    for observation in observations {
        if let topCandidate = observation.topCandidates(1).first {
            print(topCandidate.string)
        }
    }
}
request.recognitionLevel = .accurate
request.recognitionLanguages = ["id-ID", "en-US"]

let handler = VNImageRequestHandler(cgImage: image)
try handler.perform([request])

// natural-language: Sentiment analysis
import NaturalLanguage

let tagger = NLTagger(tagSchemes: [.sentimentScore])
tagger.string = "Aplikasi ini sangat menarik dan mudah digunakan!"
let (sentiment, _) = tagger.tag(at: tagger.string!.startIndex, unit: .paragraph, scheme: .sentimentScore)
let score = Double(sentiment?.rawValue ?? "0") ?? 0
// score: -1.0 (negatif) sampai 1.0 (positif)

// speech: Live transcription
import Speech

let recognizer = SFSpeechRecognizer(locale: Locale(identifier: "id-ID"))
let request = SFSpeechAudioBufferRecognitionRequest()
request.shouldReportPartialResults = true
request.requiresOnDeviceRecognition = true  // privacy mode

let task = recognizer?.recognitionTask(with: request) { result, error in
    if let result {
        print(result.bestTranscription.formattedString)
    }
}