Convert various audio files (.wav, .mp3, .ogg) to wav files, support minute and second level segmentation

Convert various audio files (.wav, .mp3, .ogg) to wav files, support minute and second level segmentation

Requirements : Call the python script, input the source file path, target path, cutting duration, and the time unit of the cutting duration , and be able to cut the source audio file corresponding to the path into the target path according to the set cutting duration.

Final effect :

According to cutting every 8 minutes:

Note : If there is no corresponding dependency package, you need to download it yourself through the pip3 command (pydub, ffmpge)
[If you have similar problems, you can refer to this article]
(https://blog.csdn.net/baidu_38903149/article/details/ 105680450)
Code : audio_to_wav.py (multiple audios converted to wav audio)

import os
from pydub import AudioSegment


# 支持的格式
SUPPORTED_FORMATES = [".mp3", ".m4a", ".wav", ".flac", ".ogg", ".flv"]

def audios_to_wavs(src_path, res_path):
    """
    src_path目录下的所有音频文件进行 ——> 常见音频格式转wav格式
    :param src_path: 源音频存在的目录
    :param res_path: 转换后的音频存储路径
    :return:
    """
    if(os.path.exists(src_path) == False or os.path.exists(res_path) == False):
        print("路径出错，请确认src_path和res_path存在")
        exit(-1)
    # 支持的音频格式列表
    supported_formats = SUPPORTED_FORMATES
    # 记录转换的总文件数
    count = 0
    # 循环遍历文件夹中的所有音频文件
    for audio_file in os.listdir(src_path):
        # 检查文件是否为支持的音频格式
        if audio_file.endswith(tuple(supported_formats)):
            # 获取不带扩展名的文件名
            file_name = os.path.splitext(audio_file)[0]
            # 使用pydub读取音频文件
            audio = AudioSegment.from_file(os.path.join(src_path, audio_file))
            # 将音频文件导出为wav格式
            audio.export(os.path.join(res_path, file_name + ".wav"), format="wav")
            count = count + 1
    print(count)


def audio_to_wav(src_path, res_path):
    """
    单个文件 ——> 常见音频格式转wav格式
    :param src_path: 源音频路径
    :param res_path: 转换后的音频存储路径
    :return:
    """
    if(os.path.exists(src_path) == False or os.path.exists(res_path) == False):
        print("路径出错，请确认src_path和res_path存在")
        exit(-1)
    # 支持的音频格式列表
    supported_formats = SUPPORTED_FORMATES
    # 检查文件是否为支持的音频格式
    if src_path.endswith(tuple(supported_formats)):
        # 获取不带扩展名的文件名
        file_name = os.path.splitext(os.path.basename(src_path))[0]
        # 使用pydub读取音频文件
        audio = AudioSegment.from_file(src_path)
        # 将音频文件导出为wav格式
        audio.export(os.path.join(res_path, file_name + ".wav"), format="wav")
    else:
        print("目前仅支持" + supported_formats + "进行格式转换")
    print(src_path + "转换完成~")


if __name__ == '__main__':
    # audio目录下的所有音频文件，不包含子目录
    audios_to_wavs("D:\\TAL\\音视频脚本测试数据\\audio\\", "D:\\TAL\\音视频脚本测试数据\\wav\\");
    # audio_to_wav("D:\\TAL\\音视频脚本测试数据\\audio\\sent.mp3", "D:\\TAL\\音视频脚本测试数据\\wav");

Code : wav_split.py (wav audio cutting script)

import os.path

from pydub import AudioSegment


def wav_split(wav_path, part_path, split_time):
    """
    音频切片，获取部分音频，单位秒
    :param wav_path: 原音频文件路径
    :param splitTime: 切割时长(s)
    :param part_path: 截取后的音频路径
    :return:
    """
    if(os.path.exists(wav_path) == False or os.path.exists(part_path) == wav_path):
        print("路径出错，请确认wav_path和part_path存在")
        exit(-1)

    file_name = os.path.splitext(os.path.basename(wav_path))[0] # wav文件名
    dir_part_path = os.path.join(part_path, file_name) # 以file_name生成目录存放对应音频切割的文件
    if(os.path.exists(dir_part_path) == False):
        os.mkdir(dir_part_path)
    sound = AudioSegment.from_wav(wav_path) # wav音频数据
    duration = sound.duration_seconds  # 音频时长（s）
    nframes = duration // split_time if (duration % split_time == 0) else duration // split_time + 1 # 分割后的段数
    for i in range(int(nframes)):
        # 该段对应的起始时间
        start = i * split_time
        # 该段对应的结束时间
        if (i != nframes - 1):
            end = start + split_time
        else:
            end = duration
        # 分割后的路径
        tempPath = os.path.join(dir_part_path, file_name + "_" + str(i * split_time) + "_" + str((i + 1) * split_time) + "s.wav")
        get_second_part_wav(wav_path, start, end, tempPath)
        print(tempPath + "已切割成功！")


def wavs_split(wav_dir, part_path, split_time):
    """
    音频切片，获取部分音频，单位秒
    :param wav_dir: 音频目录
    :param splitTime: 切割时长(s)
    :param part_path: 截取后的音频路径
    :return:
    """
    if(os.path.exists(wav_dir) == False or os.path.exists(part_path) == False):
        print("路径出错，请确认wav_dir和part_path存在")
        exit(-1)

    for src_wav in os.listdir(wav_dir):
        filename = os.path.join(wav_dir, os.path.basename(src_wav))
        wav_split(filename, part_path, split_time)
        print(filename + "已切割完毕~")


def get_second_part_wav(main_wav_path, start_time, end_time, part_wav_path):
    """
    音频切片，获取部分音频，单位秒
    :param main_wav_path: 原音频文件路径
    :param start_time: 截取的开始时间
    :param end_time: 截取的结束时间
    :param part_wav_path: 截取后的音频路径
    :return:
    """
    start_time = start_time * 1000
    end_time = end_time * 1000
    sound = AudioSegment.from_wav(main_wav_path)
    word = sound[start_time:end_time]
    try:
        word.export(part_wav_path, format="wav")
    except FileNotFoundError:
        print("存储路径不存在！请使用正确的存储路径")
        exit(-1)

if __name__ == '__main__':
    # 单个文件切割
    # wav_split('D:\\TAL\\音视频脚本测试数据\\wavs\\1.wav', 'D:\\TAL\\音视频脚本测试数据\\split_wav', 2)
    # 目录文件切割
    wavs_split('D:\\TAL\\音视频脚本测试数据\\wavs', 'D:\\TAL\\音视频脚本测试数据\\splits', 2)