Update app.py

app.py

@@ -60,4 +60,77 @@ def wav_bytes_from_spectrogram_image(image: Image.Image) -> T.Tuple[io.BytesIO,
 
     return wav_bytes
 
+def spectrogram_from_image(
+    image: Image.Image, max_volume: float = 50, power_for_image: float = 0.25
+) -> np.ndarray:
+    """
+    Compute a spectrogram magnitude array from a spectrogram image.
+    TODO(hayk): Add image_from_spectrogram and call this out as the reverse.
+    """
+    # Convert to a numpy array of floats
+    data = np.array(image).astype(np.float32)
+
+    # Flip Y take a single channel
+    data = data[::-1, :, 0]
+
+    # Invert
+    data = 255 - data
+
+    # Rescale to max volume
+    data = data * max_volume / 255
+
+    # Reverse the power curve
+    data = np.power(data, 1 / power_for_image)
+
+    return data
+
+def waveform_from_spectrogram(
+    Sxx: np.ndarray,
+    n_fft: int,
+    hop_length: int,
+    win_length: int,
+    num_samples: int,
+    sample_rate: int,
+    mel_scale: bool = True,
+    n_mels: int = 512,
+    max_mel_iters: int = 200,
+    num_griffin_lim_iters: int = 32,
+    device: str = "cuda:0",
+) -> np.ndarray:
+    """
+    Reconstruct a waveform from a spectrogram.
+    This is an approximate inverse of spectrogram_from_waveform, using the Griffin-Lim algorithm
+    to approximate the phase.
+    """
+    Sxx_torch = torch.from_numpy(Sxx).to(device)
+
+    # TODO(hayk): Make this a class that caches the two things
+
+    if mel_scale:
+        mel_inv_scaler = torchaudio.transforms.InverseMelScale(
+            n_mels=n_mels,
+            sample_rate=sample_rate,
+            f_min=0,
+            f_max=10000,
+            n_stft=n_fft // 2 + 1,
+            norm=None,
+            mel_scale="htk",
+            max_iter=max_mel_iters,
+        ).to(device)
+
+        Sxx_torch = mel_inv_scaler(Sxx_torch)
+
+    griffin_lim = torchaudio.transforms.GriffinLim(
+        n_fft=n_fft,
+        win_length=win_length,
+        hop_length=hop_length,
+        power=1.0,
+        n_iter=num_griffin_lim_iters,
+    ).to(device)
+
+    waveform = griffin_lim(Sxx_torch).cpu().numpy()
+
+    return waveform
+
+
 gr.Interface(fn=wav_bytes_from_spectrogram_image, inputs=[gr.Image()], outputs=[gr.Audio()]).launch()