import gradio as gr import matplotlib.pyplot as plt import numpy as np import os import soundfile as sf def create_spectrogram_and_get_info(audio_file): # Clear figure in case it has data in it plt.clf() # Read the audio data from the file audio_data, sample_rate = sf.read(audio_file) # Flatten the audio data if it's not mono audio_data = audio_data.flatten() if len(audio_data.shape) > 1 else audio_data # Create the spectrogram plt.specgram(audio_data, Fs=sample_rate / 1, NFFT=4096, sides='onesided', cmap="Reds_r", scale_by_freq=True, scale='dB', mode='magnitude') # Save the spectrogram to a PNG file plt.savefig('spectrogram.png') # Get the audio file info audio_info = sf.info(audio_file) bit_depth = {'PCM_16': 16, 'FLOAT': 32}.get(audio_info.subtype, 0) # Convert duration to minutes, seconds, and milliseconds minutes, seconds = divmod(audio_info.duration, 60) seconds, milliseconds = divmod(seconds, 1) milliseconds *= 1000 # convert from seconds to milliseconds # Convert bitrate to Mb/s bitrate = audio_info.samplerate * audio_info.channels * bit_depth / 8 / 1024 / 1024 # Create a table with the audio file info info_table = f""" # Ilaria Audio Analyzer 💖 Audio Analyzer Software by Ilaria, Help me on Ko-Fi Special thanks to Alex Murkoff for helping me coding it! Need help with AI? Join AI Hub! | Information | Value | | --- | --- | | Duration | {int(minutes)} minutes - {int(seconds)} seconds - {int(milliseconds)} milliseconds | | Samples per second | {audio_info.samplerate} Hz | | Audio Channels | {audio_info.channels} | | Bitrate | {bitrate:.2f} Mb/s | | Extension | {os.path.splitext(audio_file)[1]} | """ # Return the PNG file of the spectrogram and the info table return info_table, 'spectrogram.png' # Create the Gradio interface iface = gr.Interface(fn=create_spectrogram_and_get_info, inputs=gr.Audio(type="filepath"), outputs=["markdown", "image"]) iface.launch()