胡俊逸

def audio2feat(self,audio_path): # get the sample rate of the audio result = self.model.transcribe(audio_path) embed_list = [] for emb in result['segments']: encoder_embeddings = emb['encoder_embeddings'] encoder_embeddings = encoder_embeddings.transpose(0,2,1,3) encoder_embeddings = encoder_embeddings.squeeze(0) start_idx...