video-translate-v0.5.2

Voice recognition adopts the offline model openai-whisper to perform speech-to-text conversion.

Adding a Spleeter to remove background music to improve the accuracy of the results.

Adding CLI mode

Adding Whisper model select

语音识别采用 openai-whisper 离线模型，

添加 Spleeter 去除背景音乐，以便结果更准确

增加 cli 模式

增加whisper模型选择