python - 我想在 azure 语音服务中添加单词级时间戳以进行连续识别

Question

def speech_recognize_continuous_from_file():
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    speech_config.request_word_level_timestamps()
    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

all_results = {}
all_results['output'] = []
def handle_final_result(evt):
    all_results['output'].append({
        'result_id': evt.result.result_id,
        'text': evt.result.text
    })

speech_recognizer.recognized.connect(handle_final_result)

# 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
result=speech_recognizer.start_continuous_recognition()
print(result.json)
stt = json.loads(result.json)
confidences_in_nbest = [item['Confidence'] for item in stt['NBest']]
best_index = confidences_in_nbest.index(max(confidences_in_nbest))
words = stt['NBest'][best_index]['Words']
print(words)
print(f"Word\tOffset\tDuration")
for word in words:
    print(f"{word['Word']}\t{word['Offset']}\t{word['Duration']}")
while not done:
    time.sleep(.5)

print("Printing all results:")
print(all_results)
with open('response.json', 'w') as outfile:
    json.dump(all_results, outfile)

Answer 1

可以这样做，而不是执行此操作，而是可以将音频片段化为一堆音频文件，如果不接收完整文件，则将其提供给Azure。然后，最后将所有文件的输出合并为一个。