I'm using Microsoft Azure's speech-to-text API and it's working well but the output is cumbersome and I'd like to clean it up so that only the recognized speech is displayed.
this is what the output looks like
The python snippet that azure provides is:
try:
import azure.cognitiveservices.speech as speechsdk
import sys
sys.exit(1)
speech_key, service_region = "***", "***"
weatherfilename = os.path.join(
os.path.dirname(__file__),
'orf_audio_2',
'716_anton.wav')
# def speech_recognize_once_from_file():
"""performs one-shot speech recognition with input from an audio file"""
# <SpeechRecognitionWithFile>
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)
# Creates a speech recognizer using a file as audio input.
# The default language is "en-us".
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
start_continuous_recognition() instead.
result = speech_recognizer.recognize_once()
# Check the result
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))
# </SpeechRecognitionWithFile>
