读取wav文件对应的label python

---

import numpy as np
from python_speech_features import mfcc  # 需要pip install
import scipy.io.wavfile as wav
import os

def get_wavs_lables(wav_path, label_file):
    # 获得训练用的wav文件路径列表
    wav_files = []
    for (dirpath, dirnames, filenames) in os.walk(wav_path):
        for filename in filenames:
            if filename.endswith('.wav') or filename.endswith('.WAV'):
                filename_path = os.sep.join([dirpath, filename])
                if os.stat(filename_path).st_size < 240000:  # 剔除掉一些小文件
                    continue
                wav_files.append(filename_path)

    labels_dict = {}
    with open(label_file, 'rb') as f:
        for label in f:
            label = label.strip(b'\n')
            label_id = label.split(b' ', 1)[0]
            label_text = label.split(b' ', 1)[1]
            labels_dict[label_id.decode('ascii')] = label_text.decode('utf-8')

    labels = []
    new_wav_files = []
    for wav_file in wav_files:
        wav_id = os.path.basename(wav_file).split('.')[0]

        if wav_id in labels_dict:
            labels.append(labels_dict[wav_id])
            new_wav_files.append(wav_file)

    return new_wav_files, labels