MuseTalk icon indicating copy to clipboard operation
MuseTalk copied to clipboard

实时推理支持音频数据流

Open jinqinn opened this issue 9 months ago • 5 comments

whisper_feature = audio_processor.audio2feat(stream) whisper_chunks = audio_processor.feature2chunks(feature_array=whisper_feature, fps=fps)

目前realtime_inference代码中的音频是基于音频文件来操作的,如何支持GPT-SOVits等实时音频流来进行实时推理呢?

jinqinn avatar May 05 '24 02:05 jinqinn