Merge pull request #736 from IAHispano/formatter/main

chore(format): run black on main

rvc/train/extract/extract.py

@@ -272,9 +272,11 @@ def run_embedding_extraction(
             data = json.load(f)
     else:
         data = {}
-    data.update({
-        "embedder_model": chosen_embedder_model,
-    })
+    data.update(
+        {
+            "embedder_model": chosen_embedder_model,
+        }
+    )
     with open(file_path, "w") as f:
         json.dump(data, f, indent=4)
 

rvc/train/extract/preparing_files.py

@@ -39,27 +39,39 @@ def generate_filelist(
         sid = name.split("_")[0]
         if sid not in sids:
             sids.append(sid)
-        options.append(f"{gt_wavs_dir}/{name}.wav|{feature_dir}/{name}.npy|{f0_dir}/{name}.wav.npy|{f0nsf_dir}/{name}.wav.npy|{sid}")
+        options.append(
+            f"{gt_wavs_dir}/{name}.wav|{feature_dir}/{name}.npy|{f0_dir}/{name}.wav.npy|{f0nsf_dir}/{name}.wav.npy|{sid}"
+        )
 
-    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"{rvc_version}_extracted", "mute.npy")
+    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"{rvc_version}_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")
 
     # always adding two files
     for sid in sids:
-        options.append(f"{mute_audio_path}|{mute_feature_path}|{mute_f0_path}|{mute_f0nsf_path}|{sid}")
-        options.append(f"{mute_audio_path}|{mute_feature_path}|{mute_f0_path}|{mute_f0nsf_path}|{sid}")
+        options.append(
+            f"{mute_audio_path}|{mute_feature_path}|{mute_f0_path}|{mute_f0nsf_path}|{sid}"
+        )
+        options.append(
+            f"{mute_audio_path}|{mute_feature_path}|{mute_f0_path}|{mute_f0nsf_path}|{sid}"
+        )
 
     file_path = os.path.join(model_path, "model_info.json")
     if os.path.exists(file_path):
         with open(file_path, "r") as f:
             data = json.load(f)
     else:
         data = {}
-    data.update({
-        "speakers_id": len(sids),
-    })
+    data.update(
+        {
+            "speakers_id": len(sids),
+        }
+    )
     with open(file_path, "w") as f:
         json.dump(data, f, indent=4)
 

rvc/train/preprocess/preprocess.py

@@ -67,7 +67,7 @@ def process_audio_segment(
         sid: int,
         idx0: int,
         idx1: int,
-        process_effects: bool
+        process_effects: bool,
     ):
         normalized_audio = (
             self._normalize_audio(audio_segment) if process_effects else audio_segment
@@ -178,6 +178,7 @@ def process_audio_wrapper(args):
         reduction_strength,
     )
 
+
 def preprocess_training_set(
     input_root: str,
     sr: int,
@@ -204,13 +205,30 @@ def preprocess_training_set(
                     files.append((os.path.join(root, f), idx, sid))
                     idx += 1
         except ValueError:
-            print(f"Speaker ID folder is expected to be integer, got \"{os.path.basename(root)}\" instead.")
+            print(
+                f'Speaker ID folder is expected to be integer, got "{os.path.basename(root)}" instead.'
+            )
 
     # print(f"Number of files: {len(files)}")
     audio_length = []
     with tqdm(total=len(files)) as pbar:
-        with concurrent.futures.ProcessPoolExecutor(max_workers=num_processes) as executor:
-            futures = [executor.submit(process_audio_wrapper, (pp, file, cut_preprocess, process_effects, noise_reduction, reduction_strength,)) for file in files]
+        with concurrent.futures.ProcessPoolExecutor(
+            max_workers=num_processes
+        ) as executor:
+            futures = [
+                executor.submit(
+                    process_audio_wrapper,
+                    (
+                        pp,
+                        file,
+                        cut_preprocess,
+                        process_effects,
+                        noise_reduction,
+                        reduction_strength,
+                    ),
+                )
+                for file in files
+            ]
             for future in concurrent.futures.as_completed(futures):
                 audio_length.append(future.result())
                 pbar.update(1)

tabs/inference/inference.py

@@ -299,11 +299,13 @@ def refresh_embedders_folders():
     ]
     return custom_embedders
 
+
 def get_speakers_id(model):
     model_data = torch.load(model, map_location="cpu")
     speakers_id = model_data.get("speakers_id", 0)
     return list(range(speakers_id + 1))
 
+
 # Inference tab
 def inference_tab():
     default_weight = names[0] if names else None