Update websocket_protocol_zh.md

Yabin Li

2024-01-17 dcc310e1a8ff75df5b8d091a9e26883b85b8afec

 funasr/datasets/audio_datasets/datasets.py

@@ -1,7 +1,7 @@
import torch

from funasr.register import tables
from funasr.utils.load_utils import extract_fbank
from funasr.utils.load_utils import extract_fbank, load_audio_text_image_video


@tables.register("dataset_classes", "AudioDataset")
@@ -55,7 +55,7 @@
        # import pdb;
        # pdb.set_trace()
        source = item["source"]
        data_src = load_audio(source, fs=self.fs)
        data_src = load_audio_text_image_video(source, fs=self.fs)
        if self.preprocessor_speech:
            data_src = self.preprocessor_speech(data_src)
        speech, speech_lengths = extract_fbank(data_src, data_type=self.data_type, frontend=self.frontend) # speech: [b, T, d]