Mengonversi dan menyimpan file audio dengan PyDub

Pemrosesan Bahasa Lisan dengan Python

Daniel Bourke

Machine Learning Engineer/YouTube Creator

Mengekspor file audio

from pydub import AudioSegment

# Impor file audio
wav_file = AudioSegment.from_file("wav_file.wav")

# Tambah 10 desibel
louder_wav_file = wav_file + 10

# Ekspor file audio yang lebih keras
louder_wav_file.export(out_f="louder_wav_file.wav", format="wav")

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

Memformat ulang dan mengekspor banyak file audio

def make_wav(wrong_folder_path, right_folder_path):

    # Ulangi file yang formatnya salah
    for file in os.scandir(wrong_folder_path):

    # Hanya proses file dengan ekstensi audio yang akan diperbaiki
    if file.path.endswith(".mp3") or file.path.endswith(".flac"):

        # Buat nama file .wav baru
        out_file = right_folder_path + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

    # Baca file audio dan ekspor ke format wav
    AudioSegment.from_file(file.path).export(out_file,
                                             format="wav")

    print(f"Creating {out_file}")

Memformat ulang dan mengekspor banyak file audio

# Panggil fungsi baru kita
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

Memanipulasi dan mengekspor

def make_no_static_louder(static_quiet, louder_no_static):
    # Ulangi file dengan noise dan pelan (sudah format wav)
    for file in os.scandir(static_quiet_folder_path):

        # Buat path file baru
        out_file = louder_no_static + os.path.splitext(os.path.basename(file.path))[0] + ".wav"

        # Baca file audio
        audio_file = AudioSegment.from_file(file.path)

        # Hapus 3 detik pertama, tambah 10 desibel, lalu ekspor
        audio_file = (audio_file[3100:] + 10).export(out_file, format="wav")

        print(f"Creating {out_file}")

Memanipulasi dan mengekspor

# Hapus noise dan buat lebih keras
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

Ayo berlatih!

Pemrosesan Bahasa Lisan dengan Python