使用 PyDub 轉換並儲存音訊檔

Python 的口語語言處理

Daniel Bourke

Machine Learning Engineer/YouTube Creator

匯出音訊檔

from pydub import AudioSegment

# 匯入音訊檔
wav_file = AudioSegment.from_file("wav_file.wav")

# 提升 10 分貝
louder_wav_file = wav_file + 10

# 匯出較大聲的音訊檔
louder_wav_file.export(out_f="louder_wav_file.wav", format="wav")

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

批次重新格式化並匯出多個音訊檔

def make_wav(wrong_folder_path, right_folder_path):

    # 走訪格式錯誤的檔案
    for file in os.scandir(wrong_folder_path):

    # 只處理要修正的音訊副檔名
    if file.path.endswith(".mp3") or file.path.endswith(".flac"):

        # 建立新的 .wav 檔名
        out_file = right_folder_path + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

    # 讀取音訊並以 wav 格式匯出
    AudioSegment.from_file(file.path).export(out_file,
                                             format="wav")

    print(f"Creating {out_file}")

批次重新格式化並匯出多個音訊檔

# 呼叫新函式
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

處理並匯出

def make_no_static_louder(static_quiet, louder_no_static):
    # 走訪含雜訊且音量小的檔案（已為 wav 格式）
    for file in os.scandir(static_quiet_folder_path):

        # 建立新的檔案路徑
        out_file = louder_no_static + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

        # 讀取音訊檔
        audio_file = AudioSegment.from_file(file.path)

        # 去除前 3 秒、提升 10 分貝並匯出
        audio_file = (audio_file[3100:] + 10).export(out_file, format="wav")

        print(f"Creating {out_file}")

處理並匯出

# 去除雜訊並放大音量
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

換你動手！

Python 的口語語言處理