Python 零散笔记

whisper 生成 srt 字幕格式

 def _whisper_result_to_srt(result):
     text = []
     for i, s in enumerate(result['segments']):
        text.append(str(i+1))time_start = s['start']
            hours, minutes, seconds = int(
               time_start/3600), (time_start/60) % 60, (time_start) % 60
        timestamp_start = "%02d:%02d:%06.3f" % (hours, minutes, seconds)
        timestamp_start = timestamp_start.replace('.', ',')
        time_end = s['end']
        hours, minutes, seconds = int(
            time_end/3600), (time_end/60) % 60, (time_end) % 60
        timestamp_end = "%02d:%02d:%06.3f" % (hours, minutes, seconds)
        timestamp_end = timestamp_end.replace('.', ',')
        text.append(timestamp_start + " --> " + timestamp_end)
        text.append(s['text'].strip() + "\n")
      return "\n".join(text)

whisperInstance = whisper.load_model('small')
result = whisperInstance.transcribe(mediaFilePath, language='fr')
srt_file = _whisper_result_to_srt(result)

时间比较

    pubTime = datetime.datetime(year, month, day, hour=0, minute=0,                                                                              second=0,microsecond=0, tzinfo=None, *, fold=0)
    days = (datetime.datetime.utcnow() - pubTime).days