[pre-commit.ci] pre-commit autoupdate

.pre-commit-config.yaml

@@ -8,12 +8,12 @@ repos:
       - id: isort
 
   - repo: https://github.com/psf/black
-    rev: 22.12.0
+    rev: 23.7.0
     hooks:
       - id: black
 
   - repo: https://github.com/codespell-project/codespell
-    rev: v2.2.4
+    rev: v2.2.5
     hooks:
       - id: codespell
         files: ^.*\.(py|md|rst|yml)$

dictionaries/ipa/sequence_phonemes.py

@@ -8,6 +8,7 @@
 phonemes_dict = yaml.safe_load(Path(__file__).with_name("symbols.yaml").open())
 # print(phonemes_dict.keys())
 
+
 # todo: add <bos>, <eos>, <pad>, <unk>, <bar> tokens
 def text_to_sequence(text):
     seq = []

fish_diffusion/archs/diffsinger/diffusions/uni_pc.py

@@ -394,15 +394,21 @@ def get_orders_and_timesteps_for_singlestep_solver(
         if order == 3:
             K = steps // 3 + 1
             if steps % 3 == 0:
-                orders = [3,] * (
+                orders = [
+                    3,
+                ] * (
                     K - 2
                 ) + [2, 1]
             elif steps % 3 == 1:
-                orders = [3,] * (
+                orders = [
+                    3,
+                ] * (
                     K - 1
                 ) + [1]
             else:
-                orders = [3,] * (
+                orders = [
+                    3,
+                ] * (
                     K - 1
                 ) + [2]
         elif order == 2:
@@ -413,7 +419,9 @@ def get_orders_and_timesteps_for_singlestep_solver(
                 ] * K
             else:
                 K = steps // 2 + 1
-                orders = [2,] * (
+                orders = [
+                    2,
+                ] * (
                     K - 1
                 ) + [1]
         elif order == 1:

fish_diffusion/modules/encoders/fast_speech.py

@@ -745,7 +745,10 @@ def forward(self, x, encoder_padding_mask=None, **kwargs):
         if self.num_heads > 0:
             residual = x
             x = self.layer_norm1(x)
-            x, _, = self.self_attn(
+            (
+                x,
+                _,
+            ) = self.self_attn(
                 query=x, key=x, value=x, key_padding_mask=encoder_padding_mask
             )
             x = F.dropout(x, self.dropout, training=self.training)

fish_diffusion/modules/vocoders/refinegan/mpd.py

@@ -15,7 +15,7 @@ def __init__(
         stride: int = 3,
         use_spectral_norm: bool = False,
         leaky_relu_slope: float = 0.2,
-        channels: Optional[list[int]] = None
+        channels: Optional[list[int]] = None,
     ) -> None:
         super(DiscriminatorP, self).__init__()
 

fish_diffusion/modules/wavenet.py

@@ -104,7 +104,6 @@ def __init__(self, d_encoder, residual_channels, use_linear_bias=False, dilation
         )
 
     def forward(self, x, conditioner, diffusion_step):
-
         diffusion_step = self.diffusion_projection(diffusion_step).unsqueeze(-1)
         conditioner = self.conditioner_projection(conditioner)
 

tools/hifisinger/gradio_ui.py

@@ -21,6 +21,7 @@
 MAX_MIXING_SPEAKERS = GLOBAL_CONFIG["max_mixing_speakers"]
 MODELS = GLOBAL_CONFIG["models"]
 
+
 # Speaker mixing component
 def get_speakers_layout(init_speakers=[], default_speaker=None):
     with gr.Blocks():

tools/mfa/postprocess_mfa.py

@@ -52,7 +52,6 @@
     list_files("dataset/mfa-data/english/LJSpeech/normed", ".wav", recursive=True)
 ):
     try:
-
         textgrid = tg.TextGrid()
         textgrid.read(str(file.with_suffix(".TextGrid")))
         words = textgrid[0]