尝试搭建本地语音转文字系统[2]

实现完上面的之后，我把一个视频，大约2h，利用格式工厂导出音频，将其进行语音识别，报错，告知需要转化为wav才能操作，这里我直接使用格式工厂对音频进行格式转化，先完成核心代码的编写。

转化完wav格式后，报错
错误很容易解决：将音频分片就行了，这里参考博客

代码参考

from paddlespeech.cli.asr.infer import ASRExecutor
import csv
# import moviepy.editor as mp
import auditok
import os
import paddle
from paddlespeech.cli.text.infer import TextExecutor

import soundfile
import librosa
import warnings

warnings.filterwarnings('ignore')

'''
音频切分
'''
# 输入类别为audio
def qiefen(path, ty='audio', mmin_dur=1, mmax_dur=100000, mmax_silence=1, menergy_threshold=55):
    audio_file = path
    audio, audio_sample_rate = soundfile.read(
        audio_file, dtype="int16", always_2d=True)

    audio_regions = auditok.split(
        audio_file,
        min_dur=mmin_dur,  # minimum duration of a valid audio event in seconds
        max_dur=mmax_dur,  # maximum duration of an event
        # maximum duration of tolerated continuous silence within an event
        max_silence=mmax_silence,
        energy_threshold=menergy_threshold  # threshold of detection
    )

    for i, r in enumerate(audio_regions):
        # Regions returned by `split` have 'start' and 'end' metadata fields
        print(
            "Region {i}: {r.meta.start:.3f}s -- {r.meta.end:.3f}s".format(i=i, r=r))

        epath = ''
        file_pre = str(epath.join(audio_file.split('.')[0].split('/')[-1]))

        mk = 'change'
        if (os.path.exists(mk) == False):
            os.mkdir(mk)
        if (os.path.exists(mk + '/' + ty) == False):
            os.mkdir(mk + '/' + ty)
        if (os.path.exists(mk + '/' + ty + '/' + file_pre) == False):
            os.mkdir(mk + '/' + ty + '/' + file_pre)
        num = i
        # 为了取前三位数字排序
        s = '000000' + str(num)

        file_save = mk + '/' + ty + '/' + file_pre + '/' + \
                    s[-3:] +