load_audio_text_image_video

游雁

2024-01-05 4f98546f3693482f8f34aa5f11ced31381c58724

 funasr/models/bicif_paraformer/model.py

@@ -23,7 +23,7 @@

from funasr.models.paraformer.search import Hypothesis

from funasr.utils.load_utils import load_audio_and_text_image_video, extract_fbank
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank
from funasr.utils import postprocess_utils
from funasr.utils.datadir_writer import DatadirWriter
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
@@ -243,7 +243,7 @@
        else:
            # extract fbank feats
            time1 = time.perf_counter()
            audio_sample_list = load_audio_and_text_image_video(data_in, fs=frontend.fs, audio_fs=kwargs.get("fs", 16000))
            audio_sample_list = load_audio_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"),