Update README.md

README.md

@@ -1,3 +1,41 @@
----
-license: mit
----
+---
+license: mit
+license_link: https://huggingface.co/nvidia/BigVGAN/blob/main/LICENSE
+tags:
+- neural-vocoder
+- audio-generation
+library_name: PyTorch
+pipeline_tag: audio-to-audio
+---
+
+## BigVGAN with different mel spectrogram input
+These BigVGAN checkpoints are from continued training of https://huggingface.co/nvidia/bigvgan_v2_24khz_100band_256x, with the input mel spectrogram generated from this code from [[vocos]](https://github.com/gemelo-ai/vocos/blob/c859e3b7b534f3776a357983029d34170ddd6fc3/vocos/feature_extractors.py#L28C1-L49C24):
+
+```py
+class MelSpectrogramFeatures(FeatureExtractor):
+    def __init__(self, sample_rate=24000, n_fft=1024, hop_length=256, n_mels=100, padding="center"):
+        super().__init__()
+        if padding not in ["center", "same"]:
+            raise ValueError("Padding must be 'center' or 'same'.")
+        self.padding = padding
+        self.mel_spec = torchaudio.transforms.MelSpectrogram(
+            sample_rate=sample_rate,
+            n_fft=n_fft,
+            hop_length=hop_length,
+            n_mels=n_mels,
+            center=padding == "center",
+            power=1,
+        )
+
+    def forward(self, audio, **kwargs):
+        if self.padding == "same":
+            pad = self.mel_spec.win_length - self.mel_spec.hop_length
+            audio = torch.nn.functional.pad(audio, (pad // 2, pad // 2), mode="reflect")
+        mel = self.mel_spec(audio)
+        features = safe_log(mel)
+        return features
+```
+
+Training was done with segment_size=65536 (unchanged) and batch_size=24 (vs 32 from the Nvidia team). Final eval PESQ is 4.340 (vs 4.362 from the Nvidia checkpoint, on their own mel spectrogram code).
+
+<center><img src="https://huggingface.co/cckm/bigvgan_melspec/resolve/main/assets/bigvgan_pesq.png" width="800"></center>