app.py

import gradio as gr

"""
Audio processing tools to convert between spectrogram images and waveforms.
"""
import io
import typing as T

import numpy as np
from PIL import Image
import pydub
from scipy.io import wavfile
import torch
import torchaudio

def wav_bytes_from_spectrogram_image(image: Image.Image) -> T.Tuple[io.BytesIO, float]:
    """
    Reconstruct a WAV audio clip from a spectrogram image. Also returns the duration in seconds.
    """

    max_volume = 50
    power_for_image = 0.25
    Sxx = spectrogram_from_image(image, max_volume=max_volume, power_for_image=power_for_image)

    sample_rate = 44100  # [Hz]
    clip_duration_ms = 5000  # [ms]

    bins_per_image = 512
    n_mels = 512

    # FFT parameters
    window_duration_ms = 100  # [ms]
    padded_duration_ms = 400  # [ms]
    step_size_ms = 10  # [ms]

    # Derived parameters
    num_samples = int(image.width / float(bins_per_image) * clip_duration_ms) * sample_rate
    n_fft = int(padded_duration_ms / 1000.0 * sample_rate)
    hop_length = int(step_size_ms / 1000.0 * sample_rate)
    win_length = int(window_duration_ms / 1000.0 * sample_rate)

    samples = waveform_from_spectrogram(
        Sxx=Sxx,
        n_fft=n_fft,
        hop_length=hop_length,
        win_length=win_length,
        num_samples=num_samples,
        sample_rate=sample_rate,
        mel_scale=True,
        n_mels=n_mels,
        max_mel_iters=200,
        num_griffin_lim_iters=32,
    )

    wav_bytes = io.BytesIO()
    wavfile.write(wav_bytes, sample_rate, samples.astype(np.int16))
    wav_bytes.seek(0)

    duration_s = float(len(samples)) / sample_rate

    return wav_bytes

gr.Interface(fn=wav_bytes_from_spectrogram_image, inputs=[gr.Image()], outputs=[gr.Audio()]).launch()