Fix style

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

@@ -27,6 +27,7 @@ DEF_LANG_TO_PHONEMIZER["en"] = DEF_LANG_TO_PHONEMIZER["en-us"]
 DEF_LANG_TO_PHONEMIZER["ja-jp"] = JA_JP_Phonemizer.name()
 DEF_LANG_TO_PHONEMIZER["zh-cn"] = ZH_CN_Phonemizer.name()
 
+
 def get_phonemizer_by_name(name: str, **kwargs) -> BasePhonemizer:
     """Initiate a phonemizer by name
 

TTS/utils/audio.py

@@ -371,7 +371,9 @@ class AudioProcessor(object):
             self.hop_length = hop_length
             self.win_length = win_length
         assert min_level_db != 0.0, " [!] min_level_db is 0"
-        assert self.win_length <= self.fft_size, f" [!] win_length cannot be larger than fft_size - {self.win_length} vs {self.fft_size}"
+        assert (
+            self.win_length <= self.fft_size
+        ), f" [!] win_length cannot be larger than fft_size - {self.win_length} vs {self.fft_size}"
         members = vars(self)
         if verbose:
             print(" > Setting up Audio Processor...")

TTS/utils/manage.py

@@ -3,8 +3,8 @@ import json
 import os
 import zipfile
 from pathlib import Path
-from typing import Tuple
 from shutil import copyfile, rmtree
+from typing import Tuple
 
 import requests
 

recipes/ljspeech/align_tts/train_aligntts.py

@@ -49,7 +49,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init model
 model = AlignTTS(config, ap, tokenizer)

recipes/ljspeech/fast_pitch/train_fast_pitch.py

@@ -84,7 +84,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init the model
 model = ForwardTTS(config, ap, tokenizer, speaker_manager=None)

recipes/ljspeech/fast_speech/train_fast_speech.py

@@ -83,7 +83,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init the model
 model = ForwardTTS(config, ap, tokenizer)

recipes/ljspeech/glow_tts/train_glowtts.py

@@ -60,7 +60,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # INITIALIZE THE MODEL
 # Models take a config object and a speaker manager as input

recipes/ljspeech/speedy_speech/train_speedy_speech.py

@@ -67,7 +67,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init model
 model = ForwardTTS(config, ap, tokenizer)

recipes/ljspeech/tacotron2-DCA/train_tacotron_dca.py

@@ -77,7 +77,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # INITIALIZE THE MODEL
 # Models take a config object and a speaker manager as input

recipes/ljspeech/tacotron2-DDC/train_tacotron_ddc.py

@@ -74,7 +74,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # INITIALIZE THE MODEL
 # Models take a config object and a speaker manager as input

recipes/ljspeech/vits_tts/train_vits.py

@@ -69,7 +69,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init model
 model = Vits(config, ap, tokenizer, speaker_manager=None)

recipes/multilingual/vits_tts/train_vits_tts.py

@@ -109,7 +109,12 @@ config.from_dict(config.to_dict())
 ap = AudioProcessor(**config.audio.to_dict())
 
 # load training samples
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it maps speaker-id to speaker-name in the model and data-loader

recipes/vctk/fast_pitch/train_fast_pitch.py

@@ -71,7 +71,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it maps speaker-id to speaker-name in the model and data-loader

recipes/vctk/fast_speech/train_fast_speech.py

@@ -69,7 +69,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it maps speaker-id to speaker-name in the model and data-loader

recipes/vctk/glow_tts/train_glow_tts.py

@@ -69,7 +69,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it maps speaker-id to speaker-name in the model and data-loader

recipes/vctk/speedy_speech/train_speedy_speech.py

@@ -69,7 +69,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it maps speaker-id to speaker-name in the model and data-loader

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

@@ -72,7 +72,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it mainly handles speaker-id to speaker-name for the model and the data-loader

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

@@ -78,7 +78,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it mainly handles speaker-id to speaker-name for the model and the data-loader

recipes/vctk/tacotron2/train_tacotron2.py

@@ -78,7 +78,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it mainly handles speaker-id to speaker-name for the model and the data-loader

recipes/vctk/vits/train_vits.py

@@ -79,7 +79,12 @@ tokenizer, config = TTSTokenizer.init_from_config(config)
 # You can define your custom sample loader returning the list of samples.
 # Or define your custom formatter and pass it to the `load_tts_samples`.
 # Check `TTS.tts.datasets.load_tts_samples` for more details.
-train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True, eval_split_max_size=config.eval_split_max_size, eval_split_size=config.eval_split_size)
+train_samples, eval_samples = load_tts_samples(
+    dataset_config,
+    eval_split=True,
+    eval_split_max_size=config.eval_split_max_size,
+    eval_split_size=config.eval_split_size,
+)
 
 # init speaker manager for multi-speaker training
 # it maps speaker-id to speaker-name in the model and data-loader