fix: remove normalization of audio in LTX Mel spectrogram creation (Comfy-Org#11990)

For LTX Audio VAE, remove normalization of audio during MEL spectrogram creation.
This aligs inference with training and prevents loud audio from being attenuated.

Author: izorinLightricks

comfy/ldm/lightricks/vae/audio_vae.py

@@ -103,20 +103,10 @@ def resample(self, waveform: torch.Tensor, source_rate: int) -> torch.Tensor:
             return waveform
         return torchaudio.functional.resample(waveform, source_rate, self.target_sample_rate)
 
-    @staticmethod
-    def normalize_amplitude(
-        waveform: torch.Tensor, max_amplitude: float = 0.5, eps: float = 1e-5
-    ) -> torch.Tensor:
-        waveform = waveform - waveform.mean(dim=2, keepdim=True)
-        peak = torch.max(torch.abs(waveform)) + eps
-        scale = peak.clamp(max=max_amplitude) / peak
-        return waveform * scale
-
     def waveform_to_mel(
         self, waveform: torch.Tensor, waveform_sample_rate: int, device
     ) -> torch.Tensor:
         waveform = self.resample(waveform, waveform_sample_rate)
-        waveform = self.normalize_amplitude(waveform)
 
         mel_transform = torchaudio.transforms.MelSpectrogram(
             sample_rate=self.target_sample_rate,