使用 PyDub 转换并保存音频文件

Python 语音语言处理

Daniel Bourke

Machine Learning Engineer/YouTube Creator

导出音频文件

from pydub import AudioSegment

# 导入音频文件
wav_file = AudioSegment.from_file("wav_file.wav")

# 增加 10 分贝
louder_wav_file = wav_file + 10

# 导出增益后的音频
louder_wav_file.export(out_f="louder_wav_file.wav", format="wav")

<_io.BufferedRandom name='louder_wav_file.wav'>

批量重新格式化并导出音频

def make_wav(wrong_folder_path, right_folder_path):

    # 遍历格式不正确的文件
    for file in os.scandir(wrong_folder_path):

    # 仅处理需修复的音频扩展名
    if file.path.endswith(".mp3") or file.path.endswith(".flac"):

        # 生成新的 .wav 文件名
        out_file = right_folder_path + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

    # 读取音频并导出为 wav
    AudioSegment.from_file(file.path).export(out_file,
                                             format="wav")

    print(f"Creating {out_file}")

批量重新格式化并导出音频

# 调用新函数
make_wav("data/wrong_formats/", "data/right_format/")

Creating data/right_types/wav_file.wav
Creating data/right_types/flac_file.wav
Creating data/right_types/mp3_file.wav

处理并导出

def make_no_static_louder(static_quiet, louder_no_static):
    # 遍历含噪且音量低的 wav 文件
    for file in os.scandir(static_quiet_folder_path):

        # 生成新路径
        out_file = louder_no_static + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

        # 读取音频
        audio_file = AudioSegment.from_file(file.path)

        # 去除前 3 秒，+10 分贝并导出
        audio_file = (audio_file[3100:] + 10).export(out_file, format="wav")

        print(f"Creating {out_file}")

处理并导出

# 去噪并增益
make_no_static_louder("data/static_quiet/", "data/louder_no_static/")

Creating data/louder_no_static/speech-recognition-services.wav
Creating data/louder_no_static/order-issue.wav
Creating data/louder_no_static/help-with-acount.wav

轮到您了！

Python 语音语言处理