funasr1.0

游雁

2024-01-05 32905d8cdedd53dad26680b0bd41397aaf0e51ae

 funasr/models/fsmn_vad/model.py

@@ -9,7 +9,7 @@
from typing import Optional
import time
from funasr.register import tables
from funasr.datasets.audio_datasets.load_audio_extract_fbank import load_audio,extract_fbank
from funasr.utils.load_utils import load_audio_and_text_image_video,extract_fbank
from funasr.utils.datadir_writer import DatadirWriter
from torch.nn.utils.rnn import pad_sequence

@@ -544,7 +544,7 @@
        else:
            # extract fbank feats
            time1 = time.perf_counter()
            audio_sample_list = load_audio(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
            audio_sample_list = load_audio_and_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
            time2 = time.perf_counter()
            meta_data["load_data"] = f"{time2 - time1:0.3f}"
            speech, speech_lengths = extract_fbank(audio_sample_list, data_type=kwargs.get("data_type", "sound"),