Fix DelightfulTTS (#2823)

* Fix tests

* Make style

recipes/bel-alex73/dump_config.py

@@ -1,7 +1,8 @@
-from train_glowtts import config
 import json
 import re
 
+from train_glowtts import config
+
 s = json.dumps(config, default=vars, indent=2)
-s = re.sub(r'"test_sentences":\s*\[\],', '', s)
+s = re.sub(r'"test_sentences":\s*\[\],', "", s)
 print(s)

recipes/bel-alex73/train_glowtts.py

@@ -3,30 +3,31 @@ import os
 # Trainer: Where the ✨️ happens.
 # TrainingArgs: Defines the set of arguments of the Trainer.
 from trainer import Trainer, TrainerArgs
-from TTS.tts.configs.shared_configs import BaseAudioConfig
 
 # GlowTTSConfig: all model related values for training, validating and testing.
 from TTS.tts.configs.glow_tts_config import GlowTTSConfig
 
 # BaseDatasetConfig: defines name, formatter and path of the dataset.
-from TTS.tts.configs.shared_configs import BaseDatasetConfig, CharactersConfig
+from TTS.tts.configs.shared_configs import BaseAudioConfig, BaseDatasetConfig, CharactersConfig
 from TTS.tts.datasets import load_tts_samples
 from TTS.tts.models.glow_tts import GlowTTS
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.utils.audio import AudioProcessor
 
 # we use the same path as this script as our training folder.
-output_path = '/storage/output-glowtts/'
+output_path = "/storage/output-glowtts/"
 
 
 # DEFINE DATASET CONFIG
 # Set LJSpeech as our target dataset and define its path.
 # You can also use a simple Dict to define the dataset and pass it to your custom formatter.
 dataset_config = BaseDatasetConfig(
-    formatter="bel_tts_formatter", meta_file_train="ipa_final_dataset.csv", path=os.path.join(output_path, "/storage/filtered_dataset/")
+    formatter="bel_tts_formatter",
+    meta_file_train="ipa_final_dataset.csv",
+    path=os.path.join(output_path, "/storage/filtered_dataset/"),
 )
 
-characters=CharactersConfig(
+characters = CharactersConfig(
     characters_class="TTS.tts.utils.text.characters.Graphemes",
     pad="_",
     eos="~",
@@ -71,22 +72,21 @@ config = GlowTTSConfig(
 )
 
 if __name__ == "__main__":
-
-# INITIALIZE THE AUDIO PROCESSOR
-# Audio processor is used for feature extraction and audio I/O.
-# It mainly serves to the dataloader and the training loggers.
+    # INITIALIZE THE AUDIO PROCESSOR
+    # Audio processor is used for feature extraction and audio I/O.
+    # It mainly serves to the dataloader and the training loggers.
     ap = AudioProcessor.init_from_config(config)
 
-# INITIALIZE THE TOKENIZER
-# Tokenizer is used to convert text to sequences of token IDs.
-# If characters are not defined in the config, default characters are passed to the config
+    # INITIALIZE THE TOKENIZER
+    # Tokenizer is used to convert text to sequences of token IDs.
+    # If characters are not defined in the config, default characters are passed to the config
     tokenizer, config = TTSTokenizer.init_from_config(config)
 
-# LOAD DATA SAMPLES
-# Each sample is a list of ```[text, audio_file_path, speaker_name]```
-# 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.
+    # LOAD DATA SAMPLES
+    # Each sample is a list of ```[text, audio_file_path, speaker_name]```
+    # 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,
@@ -94,18 +94,18 @@ if __name__ == "__main__":
         eval_split_size=config.eval_split_size,
     )
 
-# INITIALIZE THE MODEL
-# Models take a config object and a speaker manager as input
-# Config defines the details of the model like the number of layers, the size of the embedding, etc.
-# Speaker manager is used by multi-speaker models.
+    # INITIALIZE THE MODEL
+    # Models take a config object and a speaker manager as input
+    # Config defines the details of the model like the number of layers, the size of the embedding, etc.
+    # Speaker manager is used by multi-speaker models.
     model = GlowTTS(config, ap, tokenizer, speaker_manager=None)
 
-# INITIALIZE THE TRAINER
-# Trainer provides a generic API to train all the 🐸TTS models with all its perks like mixed-precision training,
-# distributed training, etc.
+    # INITIALIZE THE TRAINER
+    # Trainer provides a generic API to train all the 🐸TTS models with all its perks like mixed-precision training,
+    # distributed training, etc.
     trainer = Trainer(
         TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples
     )
 
-# AND... 3,2,1... 🚀
+    # AND... 3,2,1... 🚀
     trainer.fit()

recipes/bel-alex73/train_hifigan.py

@@ -1,15 +1,15 @@
 import os
 
-from trainer import Trainer, TrainerArgs
-from TTS.tts.configs.shared_configs import BaseAudioConfig
 from coqpit import Coqpit
+from trainer import Trainer, TrainerArgs
 
+from TTS.tts.configs.shared_configs import BaseAudioConfig
 from TTS.utils.audio import AudioProcessor
-from TTS.vocoder.configs.hifigan_config import *;
+from TTS.vocoder.configs.hifigan_config import *
 from TTS.vocoder.datasets.preprocess import load_wav_data
 from TTS.vocoder.models.gan import GAN
 
-output_path = '/storage/output-hifigan/'
+output_path = "/storage/output-hifigan/"
 
 audio_config = BaseAudioConfig(
     mel_fmin=50,
@@ -57,4 +57,4 @@ model = GAN(config, ap)
 trainer = Trainer(
     TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples
 )
-trainer.fit()
+trainer.fit()

recipes/vctk/delightful_tts/train_delightful_tts.py

@@ -5,7 +5,7 @@ from trainer import Trainer, TrainerArgs
 from TTS.config.shared_configs import BaseDatasetConfig
 from TTS.tts.configs.delightful_tts_config import DelightfulTtsAudioConfig, DelightfulTTSConfig
 from TTS.tts.datasets import load_tts_samples
-from TTS.tts.models.delightful_tts import DelightfulTtsArgs, DelightfulTTS, VocoderConfig
+from TTS.tts.models.delightful_tts import DelightfulTTS, DelightfulTtsArgs, VocoderConfig
 from TTS.tts.utils.speakers import SpeakerManager
 from TTS.tts.utils.text.tokenizer import TTSTokenizer
 from TTS.utils.audio.processor import AudioProcessor
@@ -14,7 +14,9 @@ data_path = "/raid/datasets/vctk_v092_48khz_removed_silence_silero_vad"
 output_path = os.path.dirname(os.path.abspath(__file__))
 
 
-dataset_config = BaseDatasetConfig(dataset_name="vctk", formatter="vctk", meta_file_train="", path=data_path, language="en-us")
+dataset_config = BaseDatasetConfig(
+    dataset_name="vctk", formatter="vctk", meta_file_train="", path=data_path, language="en-us"
+)
 
 audio_config = DelightfulTtsAudioConfig()
 
@@ -73,9 +75,7 @@ speaker_manager.set_ids_from_data(train_samples + eval_samples, parse_key="speak
 config.model_args.num_speakers = speaker_manager.num_speakers
 
 
-model = DelightfulTTS(
-    ap=ap, config=config, tokenizer=tokenizer, speaker_manager=speaker_manager, emotion_manager=None
-)
+model = DelightfulTTS(ap=ap, config=config, tokenizer=tokenizer, speaker_manager=speaker_manager, emotion_manager=None)
 
 trainer = Trainer(
     TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples