def init_from_config(config: Coqpit):
"""Initialize model from config."""
from TTS.utils.audio import AudioProcessor
ap = AudioProcessor.init_from_config(config)
tokenizer = TTSTokenizer.init_from_config(config)
speaker_manager = SpeakerManager.init_from_config(config)
return BaseTacotron(config, ap, tokenizer, speaker_manager)
def init_from_config(config: "ForwardTTSConfig",
samples: Union[List[List], List[Dict]] = None):
"""Initiate model from config
Args:
config (ForwardTTSConfig): Model config.
samples (Union[List[List], List[Dict]]): Training samples to parse speaker ids for training.
Defaults to None.
"""
from TTS.utils.audio import AudioProcessor
ap = AudioProcessor.init_from_config(config)
tokenizer, new_config = TTSTokenizer.init_from_config(config)
speaker_manager = SpeakerManager.init_from_config(config, samples)
return ForwardTTS(new_config, ap, tokenizer, speaker_manager)
def init_from_config(config: "GlowTTSConfig",
samples: Union[List[List], List[Dict]] = None,
verbose=True):
"""Initiate model from config
Args:
config (VitsConfig): Model config.
samples (Union[List[List], List[Dict]]): Training samples to parse speaker ids for training.
Defaults to None.
verbose (bool): If True, print init messages. Defaults to True.
"""
from TTS.utils.audio import AudioProcessor
ap = AudioProcessor.init_from_config(config, verbose)
tokenizer, new_config = TTSTokenizer.init_from_config(config)
speaker_manager = SpeakerManager.init_from_config(config, samples)
return GlowTTS(new_config, ap, tokenizer, speaker_manager)
"Es hat mich viel Zeit gekostet ein Stimme zu entwickeln, jetzt wo ich sie habe werde ich nicht mehr schweigen.",
"Sei eine Stimme, kein Echo.",
"Es tut mir Leid David. Das kann ich leider nicht machen.",
"Dieser Kuchen ist großartig. Er ist so lecker und feucht.",
"Vor dem 22. November 1963.",
],
sort_by_audio_len=True,
max_seq_len=500000,
output_path=output_path,
datasets=[dataset_config],
)
# 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
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.
train_samples, eval_samples = load_tts_samples(
dataset_config,
eval_split=True,
eval_split_max_size=config.eval_split_max_size,
def init_from_config(config: Coqpit, verbose=True) -> "GAN":
ap = AudioProcessor.init_from_config(config, verbose=verbose)
return GAN(config, ap=ap)
