Microsoft Azure Speech-to-Text MVC application

Question

I'm working on an application that uses the Microsoft Cognitive services Speech-to-Text API. I'm trying to create a GUI where the transcribed text should show up in a textbox once the start button is pushed and the transcription is stopped once a stop-button is pressed. I'm pretty new to creating GUI's and have been using PyQt5. I have divided the application according to MVC (Model-View-Controller). The code for the GUI is as follows:

import sys
import time
from functools import partial

import azure.cognitiveservices.speech as speechsdk

from PyQt5.QtCore import *
from PyQt5.QtWidgets import *
from PyQt5.QtGui import *


class test_view(QMainWindow):
    def __init__(self):
         super().__init__()
         self.generalLayout = QVBoxLayout()
         self._centralWidget = QWidget(self)
         self.setCentralWidget(self._centralWidget)
         self._centralWidget.setLayout(self.generalLayout)

         self._createApp()

    def _createApp(self):
        self.startButton = QPushButton('Start')
        self.stopButton = QPushButton('Stop')
        buttonLayout = QHBoxLayout()
        self.startButton.setFixedWidth(220)
        self.stopButton.setFixedWidth(220)
        buttonLayout.addWidget(self.startButton)
        buttonLayout.addWidget(self.stopButton)

        self.text_box = QTextEdit()
        self.text_box.setReadOnly(True)
        self.text_box.setFixedSize(1500, 400)
        layout_text = QHBoxLayout()
        layout_text.addWidget(self.text_box)
        layout_text.setAlignment(Qt.AlignCenter)

        self.generalLayout.addLayout(buttonLayout)
        self.generalLayout.addLayout(layout_text)

    def appendText(self, text):
        self.text_box.append(text)
        self.text_box.setFocus()

    def clearText(self):
         return self.text_box.setText('')


class test_ctrl:
    def __init__(self, view):
        self._view = view


def main():
    application = QApplication(sys.argv)
    view = test_view()
    view.showMaximized()
    test_ctrl(view=view)
    sys.exit(application.exec_())


if __name__ == "__main__":
   main()

The Speech-to-Text Transcribe code is:

import azure.cognitiveservices.speech as speechsdk
import time


def setupSpeech():
    speech_key, service_region = "speech_key", "service_region"
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config)

    return speech_recognizer


def main():
    speech_recognizer = setupSpeech()

    done = False

    def stop_cb(evt):
        print('CLOSING on {}'.format(evt))
        speech_recognizer.stop_continuous_recognition()
        nonlocal done
        done = True

    all_results = []

    def handle_final_result(evt):
        all_results.append(evt.result.text)

    speech_recognizer.recognizing.connect(lambda evt: print(evt))
    speech_recognizer.recognized.connect(handle_final_result)
    speech_recognizer.session_stopped.connect(stop_cb)
    speech_recognizer.canceled.connect(stop_cb)

    speech_recognizer.start_continuous_recognition()
    while not done:
        time.sleep(.5)

    print(all_results)


if __name__ == "__main__":
    main()

I know for sure that both of the pieces of code work, but I'm not sure how to build the speech-to-text code into the MVC code. I think it should work with a model and it should be connected through the controller to the view. I tried doing this in multiple ways but I just can't figure it out. I also figured I need some kind of threading to keep the code from freezing the GUI. I hope someone can help me with this.

Answer 1

You need to replace this part

print(all_results)

and push all_results asynchronously to ur code for processing the text.

If not, expose a button in the UI to invoke the speech_recognizer.start_continuous_recognition() as a separate function and pick the results to process. This way you can avoid freezing the UI