Created
April 22, 2024 20:06
-
-
Save tyleretters/d581ea0a3968437cd938d2b456a7ca67 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/Users/tyleretters/Desktop/generateWaveform/myenv/bin/python | |
import os | |
import sys | |
from pydub import AudioSegment | |
import numpy as np | |
import matplotlib.pyplot as plt | |
def generate_waveform(audio_path, image_path, color, dimensions): | |
# Load the audio file | |
audio = AudioSegment.from_file(audio_path) | |
# Get stereo or mono data | |
if audio.channels == 2: | |
left = audio.split_to_mono()[0].get_array_of_samples() | |
right = audio.split_to_mono()[1].get_array_of_samples() | |
data = np.array([left, right]) | |
else: | |
data = np.array(audio.get_array_of_samples()) | |
# Normalize the data | |
data = data / np.max(np.abs(data)) | |
# Prepare dimensions | |
width, height = map(int, dimensions.split('x')) | |
# Setup the plot | |
fig, ax = plt.subplots(figsize=(width / 100, height / 100)) | |
ax.set_facecolor('black') | |
ax.fill_between(np.arange(len(data[0])), data[0], color=color) | |
if audio.channels == 2: | |
ax.fill_between(np.arange(len(data[1])), -data[1], color=color) | |
# Remove axes | |
ax.axis('off') | |
# Save the image | |
plt.savefig(image_path, dpi=100, bbox_inches='tight', pad_inches=0) | |
plt.close() | |
def main(audio_input_dir, image_output_dir, waveform_color, png_dimensions): | |
# Ensure output directory exists | |
if not os.path.exists(image_output_dir): | |
os.makedirs(image_output_dir) | |
# Process each file in the directory | |
for filename in os.listdir(audio_input_dir): | |
if filename.endswith('.wav') or filename.endswith('.mp3'): | |
audio_path = os.path.join(audio_input_dir, filename) | |
image_filename = filename.rsplit('.', 1)[0] + '.png' | |
image_path = os.path.join(image_output_dir, image_filename) | |
generate_waveform(audio_path, image_path, waveform_color, png_dimensions) | |
print(f"Generated waveform for {filename}") | |
if __name__ == "__main__": | |
if len(sys.argv) < 5: | |
print("Usage: python script.py <audio_input_dir> <image_output_dir> <waveform_color> <png_dimensions>") | |
else: | |
main(sys.argv[1], sys.argv[2], sys.argv[3], sys.argv[4]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment