Pemrosesan Bahasa Lisan dengan Python
Daniel Bourke
Machine Learning Engineer/YouTube Creator
$ pip install pydub
.wav, instal ffmpeg via ffmpeg.org# Impor kelas utama PyDub
from pydub import AudioSegment
# Impor file audio
wav_file = AudioSegment.from_file(file="wav_file.wav", format="wav")
# Parameter format hanya untuk keterbacaan
wav_file = AudioSegment.from_file(file="wav_file.wav")
type(wav_file)
pydub.audio_segment.AudioSegment
# Instal simpleaudio untuk memutar wav
$pip install simpleaudio
# Impor fungsi play
from pydub.playback import play
# Impor file audio
wav_file = AudioSegment.from_file(file="wav_file.wav")
# Putar file audio
play(wav_file)
# Impor file audio wav_file = AudioSegment.from_file(file="wav_file.wav") two_speakers = AudioSegment.from_file(file="two_speakers.wav")# Cek jumlah kanal wav_file.channels, two_speakers.channels
1, 2
wav_file.frame_rate
480000
# Cari jumlah byte per sampel
wav_file.sample_width
2
# Cari amplitudo maksimum
wav_file.max
8488
# Durasi file audio dalam milidetik
len(wav_file)
3284
# Ubah ATTRIBUTENAME dari AudioSegment ke x
changeed_audio_segment = audio_segment.set_ATTRIBUTENAME(x)
# Ubah lebar sampel ke 1
wav_file_width_1 = wav_file.sample_width(1)
wav_file_width_1.sample_width
1
# Ubah sample rate
wav_file_16k = wav_file.frame_rate(16000)
wav_file_16k.frame_rate
16000
# Ubah jumlah kanal
wav_file_1_channel = wav_file.set_channels(1)
wav_file_1_channel.channels
1
Pemrosesan Bahasa Lisan dengan Python