chore(format): run black on main

core.py

@@ -518,9 +518,7 @@ def run_train_script(
         from rvc.lib.tools.pretrained_selector import pretrained_selector
 
         if custom_pretrained == False:
-            pg, pd = pretrained_selector(
-                str(vocoder), int(sample_rate)
-            )
+            pg, pd = pretrained_selector(str(vocoder), int(sample_rate))
         else:
             if g_pretrained_path is None or d_pretrained_path is None:
                 raise ValueError(

rvc/configs/config.py

@@ -63,6 +63,7 @@ def set_cuda_config(self):
             1024**3
         )
 
+
 def max_vram_gpu(gpu):
     if torch.cuda.is_available():
         gpu_properties = torch.cuda.get_device_properties(gpu)
@@ -71,6 +72,7 @@ def max_vram_gpu(gpu):
     else:
         return "8"
 
+
 def get_gpu_info():
     ngpu = torch.cuda.device_count()
     gpu_infos = []

rvc/lib/algorithm/discriminators.py

@@ -20,9 +20,7 @@ class MultiPeriodDiscriminator(torch.nn.Module):
             Defaults to False.
     """
 
-    def __init__(
-        self, use_spectral_norm: bool = False, checkpointing: bool = False
-    ):
+    def __init__(self, use_spectral_norm: bool = False, checkpointing: bool = False):
         super(MultiPeriodDiscriminator, self).__init__()
         periods = [2, 3, 5, 7, 11, 17, 23, 37]
         self.checkpointing = checkpointing

rvc/lib/algorithm/generators/refinegan.py

@@ -1,4 +1,3 @@
-import math
 import numpy as np
 import torch
 from torch.nn.utils.parametrizations import weight_norm

rvc/lib/predictors/RMVPE.py

@@ -435,7 +435,8 @@ def __init__(self, model_path, device=None):
         self.model = model
         self.resample_kernel = {}
         self.device = device
-        self.mel_extractor = MelSpectrogram(N_MELS, 16000, 1024, 160, None, 30, 8000
+        self.mel_extractor = MelSpectrogram(
+            N_MELS, 16000, 1024, 160, None, 30, 8000
         ).to(device)
         self.model = self.model.to(device)
         cents_mapping = 20 * np.arange(N_CLASS) + 1997.3794084376191

rvc/train/extract/extract.py

@@ -232,9 +232,7 @@ def run_embedding_extraction(
             file,
             os.path.join(exp_dir, "f0", file_name + ".npy"),
             os.path.join(exp_dir, "f0_voiced", file_name + ".npy"),
-            os.path.join(
-                exp_dir, "extracted", file_name.replace("wav", "npy")
-            ),
+            os.path.join(exp_dir, "extracted", file_name.replace("wav", "npy")),
         ]
         files.append(file_info)
 

rvc/train/extract/preparing_files.py

@@ -15,9 +15,7 @@ def generate_config(sample_rate: int, model_path: str):
         shutil.copyfile(config_path, config_save_path)
 
 
-def generate_filelist(
-    model_path: str, sample_rate: int, include_mutes: int = 2
-):
+def generate_filelist(model_path: str, sample_rate: int, include_mutes: int = 2):
     gt_wavs_dir = os.path.join(model_path, "sliced_audios")
     feature_dir = os.path.join(model_path, f"extracted")
 
@@ -47,9 +45,7 @@ def generate_filelist(
         mute_audio_path = os.path.join(
             mute_base_path, "sliced_audios", f"mute{sample_rate}.wav"
         )
-        mute_feature_path = os.path.join(
-            mute_base_path, f"extracted", "mute.npy"
-        )
+        mute_feature_path = os.path.join(mute_base_path, f"extracted", "mute.npy")
         mute_f0_path = os.path.join(mute_base_path, "f0", "mute.wav.npy")
         mute_f0nsf_path = os.path.join(mute_base_path, "f0_voiced", "mute.wav.npy")
 

rvc/train/process/extract_index.py

@@ -48,7 +48,6 @@
                 .cluster_centers_
             )
 
-
         n_ivf = min(int(16 * np.sqrt(big_npy.shape[0])), big_npy.shape[0] // 39)
 
         # index_added

rvc/train/train.py

@@ -658,7 +658,7 @@ def train_and_evaluate(
             y_hat, ids_slice, x_mask, z_mask, (z, z_p, m_p, logs_p, m_q, logs_q) = (
                 model_output
             )
-                # slice of the original waveform to match a generate slice
+            # slice of the original waveform to match a generate slice
             if randomized:
                 wave = commons.slice_segments(
                     wave,
@@ -679,7 +679,7 @@ def train_and_evaluate(
 
             # Generator backward and update
             _, y_d_hat_g, fmap_r, fmap_g = net_d(wave, y_hat)
-            
+
             loss_mel = fn_mel_loss(wave, y_hat) * config.train.c_mel / 3.0
             loss_env = envelope_loss(wave, y_hat)
             loss_kl = kl_loss(z_p, logs_q, m_p, logs_p, z_mask) * config.train.c_kl
@@ -741,7 +741,7 @@ def train_and_evaluate(
 
             pbar.update(1)
         # end of batch train
-    #end of tqdm
+    # end of tqdm
     with torch.no_grad():
         torch.cuda.empty_cache()
 

rvc/train/utils.py

@@ -112,7 +112,7 @@ def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path)
             ".parametrizations.weight.original0",
             ".weight_g",
         ),
-        checkpoint_path
+        checkpoint_path,
     )
 
     print(f"Saved model '{checkpoint_path}' (epoch {iteration})")

tabs/train/train.py

@@ -872,17 +872,17 @@ def disable_stop_train_button():
                 }
 
             def download_prerequisites():
-                    gr.Info(
-                        "Checking for prerequisites with pitch guidance... Missing files will be downloaded. If you already have them, this step will be skipped."
-                    )
-                    run_prerequisites_script(
-                        pretraineds_hifigan=True,
-                        models=False,
-                        exe=False,
-                    )
-                    gr.Info(
-                        "Prerequisites check complete. Missing files were downloaded, and you may now start preprocessing."
-                    )
+                gr.Info(
+                    "Checking for prerequisites with pitch guidance... Missing files will be downloaded. If you already have them, this step will be skipped."
+                )
+                run_prerequisites_script(
+                    pretraineds_hifigan=True,
+                    models=False,
+                    exe=False,
+                )
+                gr.Info(
+                    "Prerequisites check complete. Missing files were downloaded, and you may now start preprocessing."
+                )
 
             def toggle_visible_embedder_custom(embedder_model):
                 if embedder_model == "custom":