optimize ComputeDecibel in fsmn-vad model by using numpy (#2174)

StevenH

2024-10-26 1254e8aee1e3200acc2b4752c6822bfc1a21b22f

 funasr/models/normalize/utterance_mvn.py

@@ -5,6 +5,7 @@
from funasr.models.transformer.utils.nets_utils import make_pad_mask
from funasr.register import tables


@tables.register("normalize_classes", "UtteranceMVN")
class UtteranceMVN(torch.nn.Module):
    def __init__(