【发布时间】：2020-06-24 11:31:02
【问题描述】：
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。我已经按照其他人在这里回答的关于获取单个单词的提示进行了操作，但即使将它们格式化为 .srt 或 .vtt 似乎也很复杂。 代码如下：
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 in results['NBest']]
max_confidence_index = confidence_list_temp.index(max(confidence_list_temp))
words.extend(results['NBest'][max_confidence_index]['Words'])
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
print("Transcript display list:\n")
print(transcript)
print("\nWords\n")
print(words)
print("\n")
speech_recognizer.recognized.connect(handle_final_result)
# Connect callbacks to the events fired by the speech recognizer
speech_recognizer.recognizing.connect(lambda evt: format(evt))
speech_recognizer.recognized.connect(lambda evt: format(evt))
speech_recognizer.session_started.connect(lambda evt: format(evt))
speech_recognizer.session_stopped.connect(lambda evt: format(evt))
speech_recognizer.canceled.connect(lambda evt: 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)
with open('Azure_Raw.txt','w') as f:
f.write('\n'.join(results))
sample_long_running_recognize(storage_uri)
我在字幕上找到的唯一其他“教程”是 Google Cloud 的，它给出了我正在寻找的结果（是的，我自己测试过），但 Azure 显然根本不像 G-云：https://medium.com/searce/generate-srt-file-subtitles-using-google-clouds-speech-to-text-api-402b2f1da3bd
所以基本上：我如何将 3 秒的语音文本转换为 .srt 格式，如下所示：
1
00:00:00,000 --> 00:00:03,000
This is the first sentence that
2
00:00:03,000 --> 00:00:06,000
continues after 3 seconds or so
【问题讨论】：
标签： python azure speech-recognition speech-to-text subtitle