Make style

TTS/tts/models/base_tacotron.py

@@ -252,7 +252,12 @@ class BaseTacotron(BaseTTS):
 
     def compute_capacitron_VAE_embedding(self, inputs, reference_mel_info, text_info=None, speaker_embedding=None):
         """Capacitron Variational Autoencoder"""
-        (VAE_outputs, posterior_distribution, prior_distribution, capacitron_beta,) = self.capacitron_vae_layer(
+        (
+            VAE_outputs,
+            posterior_distribution,
+            prior_distribution,
+            capacitron_beta,
+        ) = self.capacitron_vae_layer(
             reference_mel_info,
             text_info,
             speaker_embedding,  # pylint: disable=not-callable

TTS/tts/models/tortoise.py

@@ -676,7 +676,12 @@ class Tortoise(BaseTTS):
         ), "Too much text provided. Break the text up into separate segments and re-try inference."
 
         if voice_samples is not None:
-            (auto_conditioning, diffusion_conditioning, _, _,) = self.get_conditioning_latents(
+            (
+                auto_conditioning,
+                diffusion_conditioning,
+                _,
+                _,
+            ) = self.get_conditioning_latents(
                 voice_samples,
                 return_mels=True,
                 latent_averaging_mode=latent_averaging_mode,

recipes/ljspeech/xtts_v1/train_gpt_xtts.py

@@ -97,9 +97,7 @@ def main():
         use_ne_hifigan=True,  # if it is true it will keep the non-enhanced keys on the output checkpoint
     )
     # define audio config
-    audio_config = XttsAudioConfig(
-        sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
-    )
+    audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
     # training parameters config
     config = GPTTrainerConfig(
         output_path=OUT_PATH,

recipes/ljspeech/xtts_v2/train_gpt_xtts.py

@@ -98,9 +98,7 @@ def main():
         gpt_use_perceiver_resampler=True,
     )
     # define audio config
-    audio_config = XttsAudioConfig(
-        sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
-    )
+    audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
     # training parameters config
     config = GPTTrainerConfig(
         output_path=OUT_PATH,

tests/xtts_tests/test_xtts_gpt_train.py

@@ -88,9 +88,7 @@ model_args = GPTArgs(
     gpt_stop_audio_token=8193,
     use_ne_hifigan=True,
 )
-audio_config = XttsAudioConfig(
-    sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
-)
+audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
 config = GPTTrainerConfig(
     epochs=1,
     output_path=OUT_PATH,

tests/xtts_tests/test_xtts_v2-0_gpt_train.py

@@ -88,9 +88,7 @@ model_args = GPTArgs(
     gpt_use_perceiver_resampler=True,
     use_ne_hifigan=True,
 )
-audio_config = XttsAudioConfig(
-    sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000
-)
+audio_config = XttsAudioConfig(sample_rate=22050, dvae_sample_rate=22050, output_sample_rate=24000)
 config = GPTTrainerConfig(
     epochs=1,
     output_path=OUT_PATH,