Make style

.gitignore

@@ -164,4 +164,5 @@ internal/*
 *_pitch.npy
 *_phoneme.npy
 wandb
-depot/*
+depot/*
+coqui_recipes/*

TTS/bin/train_tts.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import load_config, register_config
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import load_config, register_config
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models import setup_model
 

TTS/bin/train_vocoder.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import load_config, register_config
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import load_config, register_config
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.datasets.preprocess import load_wav_data, load_wav_feat_data
 from TTS.vocoder.models import setup_model

TTS/tts/models/base_tts.py

@@ -324,9 +324,9 @@ class BaseTTS(BaseModel):
             loader = DataLoader(
                 dataset,
                 batch_size=config.eval_batch_size if is_eval else config.batch_size,
-                shuffle=False,      # shuffle is done in the dataset.
+                shuffle=False,  # shuffle is done in the dataset.
                 collate_fn=dataset.collate_fn,
-                drop_last=True,     # setting this False might cause issues in AMP training.
+                drop_last=True,  # setting this False might cause issues in AMP training.
                 sampler=sampler,
                 num_workers=config.num_eval_loader_workers if is_eval else config.num_loader_workers,
                 pin_memory=False,

TTS/tts/models/vits.py

@@ -994,9 +994,9 @@ class Vits(BaseTTS):
                 print(" !! Error creating Test Sentence -", idx)
         return {"figures": test_figures, "audios": test_audios}
 
-    def test_log(self, outputs: dict, logger: "Logger", assets: dict, steps:int) -> None:
+    def test_log(self, outputs: dict, logger: "Logger", assets: dict, steps: int) -> None:
-        logger.test_audios(steps, outputs['audios'], self.ap.sample_rate)
+        logger.test_audios(steps, outputs["audios"], self.ap.sample_rate)
-        logger.test_figures(steps, outputs['figures'])
+        logger.test_figures(steps, outputs["figures"])
 
     def get_optimizer(self) -> List:
         """Initiate and return the GAN optimizers based on the config parameters.

TTS/tts/utils/text/phonemizers/espeak_wrapper.py

@@ -11,6 +11,7 @@ def is_tool(name):
 
     return which(name) is not None
 
+
 # priority: espeakng > espeak
 if is_tool("espeak-ng"):
     _DEF_ESPEAK_LIB = "espeak-ng"
@@ -116,7 +117,6 @@ class ESpeak(BasePhonemizer):
             #  ^
             self.num_skip_chars = 1
 
-
     def auto_set_espeak_lib(self) -> None:
         if is_tool("espeak-ng"):
             self._ESPEAK_LIB = "espeak-ng"
@@ -163,7 +163,7 @@ class ESpeak(BasePhonemizer):
         phonemes = ""
         for line in _espeak_exe(self._ESPEAK_LIB, args, sync=True):
             logging.debug("line: %s", repr(line))
-            phonemes += line.decode("utf8").strip()[self.num_skip_chars:]  # skip initial redundant characters
+            phonemes += line.decode("utf8").strip()[self.num_skip_chars :]  # skip initial redundant characters
         return phonemes.replace("_", separator)
 
     def _phonemize(self, text, separator=None):

recipes/ljspeech/align_tts/train_aligntts.py

@@ -1,6 +1,7 @@
 import os
 
 from trainer import Trainer, TrainerArgs
+
 from TTS.tts.configs.align_tts_config import AlignTTSConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.datasets import load_tts_samples

recipes/ljspeech/fast_pitch/train_fast_pitch.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig, BaseDatasetConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig, BaseDatasetConfig
 from TTS.tts.configs.fast_pitch_config import FastPitchConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.forward_tts import ForwardTTS

recipes/ljspeech/fast_speech/train_fast_speech.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from TTS.tts.configs.fast_speech_config import FastSpeechConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.forward_tts import ForwardTTS

recipes/ljspeech/hifigan/train_hifigan.py

@@ -1,6 +1,7 @@
 import os
 
 from trainer import Trainer, TrainerArgs
+
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.configs import HifiganConfig
 from TTS.vocoder.datasets.preprocess import load_wav_data

recipes/ljspeech/multiband_melgan/train_multiband_melgan.py

@@ -1,6 +1,7 @@
 import os
 
 from trainer import Trainer, TrainerArgs
+
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.configs import MultibandMelganConfig
 from TTS.vocoder.datasets.preprocess import load_wav_data

recipes/ljspeech/speedy_speech/train_speedy_speech.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from TTS.tts.configs.speedy_speech_config import SpeedySpeechConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.forward_tts import ForwardTTS

recipes/ljspeech/tacotron2-DCA/train_tacotron_dca.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.tacotron2_config import Tacotron2Config
 from TTS.tts.datasets import load_tts_samples

recipes/ljspeech/tacotron2-DDC/train_tacotron_ddc.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.tacotron2_config import Tacotron2Config
 from TTS.tts.datasets import load_tts_samples

recipes/ljspeech/univnet/train.py

@@ -1,6 +1,7 @@
 import os
 
 from trainer import Trainer, TrainerArgs
+
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.configs import UnivnetConfig
 from TTS.vocoder.datasets.preprocess import load_wav_data

recipes/ljspeech/vits_tts/train_vits.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.vits_config import VitsConfig
 from TTS.tts.datasets import load_tts_samples

recipes/ljspeech/wavegrad/train_wavegrad.py

@@ -1,6 +1,7 @@
 import os
 
 from trainer import Trainer, TrainerArgs
+
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.configs import WavegradConfig
 from TTS.vocoder.datasets.preprocess import load_wav_data

recipes/ljspeech/wavernn/train_wavernn.py

@@ -1,6 +1,7 @@
 import os
 
 from trainer import Trainer, TrainerArgs
+
 from TTS.utils.audio import AudioProcessor
 from TTS.vocoder.configs import WavernnConfig
 from TTS.vocoder.datasets.preprocess import load_wav_data

recipes/multilingual/vits_tts/train_vits_tts.py

@@ -1,8 +1,9 @@
 import os
 from glob import glob
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.vits_config import VitsConfig
 from TTS.tts.datasets import load_tts_samples

recipes/vctk/fast_pitch/train_fast_pitch.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from TTS.tts.configs.fast_pitch_config import FastPitchConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.forward_tts import ForwardTTS

recipes/vctk/fast_speech/train_fast_speech.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from TTS.tts.configs.fast_speech_config import FastSpeechConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.forward_tts import ForwardTTS

recipes/vctk/glow_tts/train_glow_tts.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.glow_tts_config import GlowTTSConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.datasets import load_tts_samples

recipes/vctk/speedy_speech/train_speedy_speech.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config import BaseAudioConfig, BaseDatasetConfig
 from TTS.tts.configs.speedy_speech_config import SpeedySpeechConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.forward_tts import ForwardTTS

recipes/vctk/tacotron-DDC/train_tacotron-DDC.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.tacotron_config import TacotronConfig
 from TTS.tts.datasets import load_tts_samples

recipes/vctk/tacotron2-DDC/train_tacotron2-ddc.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.tacotron2_config import Tacotron2Config
 from TTS.tts.datasets import load_tts_samples

recipes/vctk/tacotron2/train_tacotron2.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.tacotron2_config import Tacotron2Config
 from TTS.tts.datasets import load_tts_samples

recipes/vctk/vits/train_vits.py

@@ -1,7 +1,8 @@
 import os
 
-from TTS.config.shared_configs import BaseAudioConfig
 from trainer import Trainer, TrainerArgs
+
+from TTS.config.shared_configs import BaseAudioConfig
 from TTS.tts.configs.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.vits_config import VitsConfig
 from TTS.tts.datasets import load_tts_samples
@@ -57,7 +58,7 @@ config = VitsConfig(
     print_step=25,
     print_eval=False,
     mixed_precision=True,
-    max_text_len= 325,  # change this if you have a larger VRAM than 16GB
+    max_text_len=325,  # change this if you have a larger VRAM than 16GB
     output_path=output_path,
     datasets=[dataset_config],
 )