data.py

import librosa
import os

sr=16000
audio_dir = "/data/datasets/1/data_aishell/wav/test"
dir_list = os.listdir(audio_dir)
tmp = []
# print(dir_list)
for index in dir_list:
    audio_paths = os.listdir(os.path.join(audio_dir,index))
    for audio_path in audio_paths:
        y, sr = librosa.load(os.path.join(audio_dir,index,audio_path), sr=sr)
        if len(y)/sr == 14.6999375:
            print(os.path.join(audio_dir,index,audio_path))
        
        tmp.append(len(y)/sr)
# print(sorted(tmp))    
    # print(audio_paths)



# y, sr = librosa.load(audio_path, sr=16000)
# print(f"音频总长: {len(y)/sr:.2f}秒 ({len(y)}采样点)")