Automatic code formatting (#77)

Automatic code formatting

Author: Bebra777228

rvc/infer/pipeline.py

@@ -89,7 +89,7 @@ def get_f0(
             del model
         elif f0_method == "fcpe":
             model = FCPE(device=self.device, sample_rate=self.sample_rate, hop_size=self.window)
-            f0 = model.get_f0(x, p_len, filter_radius = 0.006)
+            f0 = model.get_f0(x, p_len, filter_radius=0.006)
             del model
 
         if f0 is None:
@@ -177,7 +177,7 @@ def vc(
             del hasp, arg
 
         if protect < 0.5 and pitch is not None and pitchf is not None:
-            del feats0 
+            del feats0
         del feats, padding_mask
         if torch.cuda.is_available():
             torch.cuda.empty_cache()

rvc/lib/predictors/f0.py

@@ -1,9 +1,10 @@
 import os
+
 import torch
+import torchcrepe
+from torchfcpe import spawn_bundled_infer_model
 
 from rvc.lib.predictors.RMVPE import RMVPE0Predictor
-from torchfcpe import spawn_bundled_infer_model
-import torchcrepe
 
 
 class RMVPE:
@@ -31,7 +32,7 @@ def get_f0(self, x, f0_min=50, f0_max=1100, p_len=None, model="full"):
         if not torch.is_tensor(x):
             x = torch.from_numpy(x)
 
-        batch_size = 512        
+        batch_size = 512
 
         f0, pd = torchcrepe.predict(
             x.float().to(self.device).unsqueeze(dim=0),
@@ -59,18 +60,23 @@ def __init__(self, device, sample_rate=16000, hop_size=160):
         self.hop_size = hop_size
         self.model = spawn_bundled_infer_model(self.device)
 
-    def get_f0(self, x, p_len=None, filter_radius = 0.006):
+    def get_f0(self, x, p_len=None, filter_radius=0.006):
         if p_len is None:
             p_len = x.shape[0] // self.hop_size
 
         if not torch.is_tensor(x):
             x = torch.from_numpy(x)
 
-        f0 = self.model.infer(
+        f0 = (
+            self.model.infer(
                 x.float().to(self.device).unsqueeze(0),
                 sr=self.sample_rate,
                 decoder_mode="local_argmax",
                 threshold=filter_radius,
-            ).squeeze().cpu().numpy()
+            )
+            .squeeze()
+            .cpu()
+            .numpy()
+        )
 
         return f0