src/preprocessing/visualize_audio.py

import librosa
import librosa.display
import matplotlib.pyplot as plt
import numpy as np

import sys, os
sys.path.append(os.path.join(os.path.dirname(__file__), '..'))
from config import TRAIN_AUDIO

audio_path = os.path.join(TRAIN_AUDIO, 'dia47_utt11.mp4')
audio, sr = librosa.load(audio_path, sr=16000)

# visualize the audio waveform
plt.figure(figsize=(10,3))
librosa.display.waveshow(audio, sr=sr)

plt.title("Audio Waveform")
plt.xlabel("Time")
plt.ylabel("Amplitude")

plt.show()

# visualize the spectrogram
spectrogram = librosa.feature.melspectrogram(y=audio, sr=sr)

plt.figure(figsize=(10,4))
librosa.display.specshow(
    librosa.power_to_db(spectrogram, ref=np.max),
    sr=sr,
    x_axis='time',
    y_axis='mel'
)

plt.title("Mel Spectrogram")
plt.colorbar(format='%+2.0f dB')
plt.show()