File size: 1,530 Bytes
de60a6a 458da1c a0110cc eb0bc41 77121d6 ef9fce3 a0110cc 77121d6 a0110cc 77121d6 a0110cc 6af81aa 77121d6 458da1c 6af81aa 77121d6 d0b2fc8 5a86410 77121d6 5a86410 d0b2fc8 5a86410 41bada8 77121d6 41bada8 a0110cc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 |
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)
# Create a table with the audio file info
info_table = f"""
| Informazione | Valore |
| --- | --- |
| Durata | {audio_info.duration} secondi |
| Campioni al secondo | {audio_info.samplerate} Hz |
| Canali | {audio_info.channels} |
| Bitrate | {audio_info.samplerate * audio_info.channels * bit_depth} bit/s |
| Estensione | {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()
|