Speech Recognition — co to je, technologie a princip fungování

// Rozpoznávání řeči Android SpeechRecognizer
val recognizer = SpeechRecognizer.createSpeechRecognizer(context)
recognizer.setRecognitionListener(object : RecognitionListener {
    override fun onResults(results: Bundle) {
        val text = results
            .getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION)
            ?.firstOrNull() ?: ""
        showResult(text)
    }
    override fun onPartialResults(partialResults: Bundle) {
        val partial = partialResults
            .getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION)
            ?.firstOrNull() ?: ""
        showPartial(partial)
    }
})

val intent = Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH).apply {
    putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
        RecognizerIntent.LANGUAGE_MODEL_FREE_FORM)
    putExtra(RecognizerIntent.EXTRA_LANGUAGE, "ru-RU")
}
recognizer.startListening(intent)

let recognizer = SFSpeechRecognizer(locale: Locale(identifier: "ru_RU"))
guard recognizer.isAvailable else { return }

let request = SFSpeechAudioBufferRecognitionRequest()
request.requiresOnDeviceRecognition = true
request.shouldReportPartialResults = true

recognitionTask = recognizer.recognitionTask(with: request) { result, error in
    if let result = result {
        let text = result.bestTranscription.formattedString
        let isFinal = result.isFinal
        DispatchQueue.main.async {
            textView.text = text
        }
    }
}

audioEngine.inputNode.installTap(config: bufferConfig) { buffer, _ in
    request.append(buffer)
}
audioEngine.prepare()
try audioEngine.start()

// Vosk offline ASR
val model = VoskModel("model/vosk-model-small-ru-0.22")
model.load()

val recognizer = VoskRecognizer(model, 16000.0f)
recognizer.setWords(true)

audioRecord.startRecording()
while (isListening) {
    val buffer = ByteArray(3200) // 100 ms audio
    audioRecord.read(buffer, 0, buffer.size)
    if (recognizer.acceptWaveform(buffer)) {
        val result = recognizer.result // JSON
        text += JSONObject(result).getString("text")
    }
}

// Whisper Core ML na iOS
import MLXWhisper

let model = try WhisperModel(from: "whisper-tiny")
let audio = try AudioUtils.loadAudio(url: audioURL)
let segments = try model.transcribe(audio: Audio, options: TranscribeOptions(
    language: "ru",
    wordTimestamps: true,
    temperature: 0.0
))

for segment in segments {
    print(segment.text) // konečný text s časovými razítky
}

// Hlasový asistent s Android SpeechRecognizer + TTS
recognizer.setRecognitionListener(object : RecognitionListener {
    override fun onResults(results: Bundle) {
        val query = results.getStringArrayList(
            SpeechRecognizer.RESULTS_RECOGNITION
        )?.firstOrNull() ?: return

        val intentResult = nluService.classify(query)
        textToSpeech.speak(intentResult.response)
        executeAction(intentResult.action)
    }
})