Azure 语音转文本 - 连续识别

Question

I would like to see the accuracy of the speech services from Azure, specifically speech-to-text using an audio file.

I have been reading the documentation https://docs.microsoft.com/en-us/python/api/azure-cognitiveservices-speech/?view=azure-python and playing around with a suggested code from the MS quickstar page. The code workds fine and I can get some transcription, but it just transcribes the beginning of the audio (first utterance):

import azure.cognitiveservices.speech as speechsdk

speechKey = 'xxx'
service_region = 'westus'

speech_config = speechsdk.SpeechConfig(subscription=speechKey, region=service_region, speech_recognition_language="es-MX")
audio_config = speechsdk.audio.AudioConfig(use_default_microphone=False, filename='lala.wav')

sr = speechsdk.SpeechRecognizer(speech_config, audio_config)

es = speechsdk.EventSignal(sr.recognized, sr.recognized)

result = sr.recognize_once()

if result.reason == speechsdk.ResultReason.RecognizedSpeech:
    print("Recognized: {}".format(result.text))
elif result.reason == speechsdk.ResultReason.NoMatch:
    print("No speech could be recognized: {}".format(result.no_match_details))
elif result.reason == speechsdk.ResultReason.Canceled:
    cancellation_details = result.cancellation_details
    print("Speech Recognition canceled: {}".format(cancellation_details.reason))
    if cancellation_details.reason == speechsdk.CancellationReason.Error:
        print("Error details: {}".format(cancellation_details.error_details))

Based on the documentation, looks like I have to use signals and events to capture the full audio using method start_continuous_recognition (which is not documented for python, but looks like the method and related classes are implemented). I tried to follow other examples from c# and Java but was not able to implement this in Python.

Has anyone been able to do this and provie some pointers? Thank you very much!

Answer 1

You could try this:

import azure.cognitiveservices.speech as speechsdk
import time
speech_key, service_region = "xyz", "WestEurope"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region, speech_recognition_language="it-IT")
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config)

speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
speech_recognizer.session_stopped.connect(lambda evt: print('\nSESSION STOPPED {}'.format(evt)))
speech_recognizer.recognized.connect(lambda evt: print('\n{}'.format(evt.result.text)))

print('Say a few words\n\n')
speech_recognizer.start_continuous_recognition()
time.sleep(10)
speech_recognizer.stop_continuous_recognition()

speech_recognizer.session_started.disconnect_all()
speech_recognizer.recognized.disconnect_all()
speech_recognizer.session_stopped.disconnect_all()

Remember to set your preferred language. It's not too much but it's a good starting point, and it works. I will continue experimenting.

Answer 2

Check the Azure python sample: https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/samples/python/console/speech_sample.py

Or other language samples: https://github.com/Azure-Samples/cognitive-services-speech-sdk/tree/master/samples

Basically, the below:

def speech_recognize_continuous_from_file():
    """performs continuous speech recognition with input from an audio file"""
    # <SpeechContinuousRecognitionWithFile>
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)

    speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)

    done = False

    def stop_cb(evt):
        """callback that stops continuous recognition upon receiving an event `evt`"""
        print('CLOSING on {}'.format(evt))
        speech_recognizer.stop_continuous_recognition()
        nonlocal done
        done = True

    # Connect callbacks to the events fired by the speech recognizer
    speech_recognizer.recognizing.connect(lambda evt: print('RECOGNIZING: {}'.format(evt)))
    speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)))
    speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
    speech_recognizer.session_stopped.connect(lambda evt: print('SESSION STOPPED {}'.format(evt)))
    speech_recognizer.canceled.connect(lambda evt: print('CANCELED {}'.format(evt)))
    # stop continuous recognition on either session stopped or canceled events
    speech_recognizer.session_stopped.connect(stop_cb)
    speech_recognizer.canceled.connect(stop_cb)

    # Start continuous speech recognition
    speech_recognizer.start_continuous_recognition()
    while not done:
        time.sleep(.5)
    # </SpeechContinuousRecognitionWithFile>

Answer 3

And to further improve @manyways solutions here own to collect the data.

all_results = []

def handle_final_result(evt):
    all_results.append(evt.result.text)
    speech_recognizer.recognized.connect(handle_final_result)  # to collect data at the end