我一直试图弄清楚如何使用 Python 中的 Microsoft Azure 语音识别服务制作字幕，但无法弄清楚。我遵循了其他人在这里回答的关于获取单个单词的提示，但即使将它们格式化为 .srt 或 .vtt 似乎也很复杂。这是代码：
import azure.cognitiveservices.speech as speechsdk
def speech_recognize_continuous_from_file():
"""performs continuous speech recognition with input from an audio file"""
# <SpeechContinuousRecognitionWithFile>
speech_key, service_region = "{api-key}", "{serive-region}"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
audio_filename = "{for example: video.wav}"
audio_config = speechsdk.audio.AudioConfig(filename=audio_filename)
speech_config.speech_recognition_language="en-US"
speech_config.request_word_level_timestamps()
speech_config.enable_dictation()
speech_config.output_format = speechsdk.OutputFormat(1)
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
done = False
results = []
transcript = []
words = []
def handle_final_result(evt):
import json
results = json.loads(evt.result.json)
transcript.append(results['DisplayText'])
confidence_list_temp = [item.get('Confidence') for item …