import os

from TTS.trainer import Trainer, TrainingArgs
from TTS.tts.configs import AlignTTSConfig, BaseDatasetConfig
from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.align_tts import AlignTTS
from TTS.utils.audio import AudioProcessor

output_path = os.path.dirname(os.path.abspath(__file__))

# init configs
dataset_config = BaseDatasetConfig(
    name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/")
)
config = AlignTTSConfig(
    batch_size=32,
    eval_batch_size=16,
    num_loader_workers=4,
    num_eval_loader_workers=4,
    run_eval=True,
    test_delay_epochs=-1,
    epochs=1000,
    text_cleaner="english_cleaners",
    use_phonemes=False,
    phoneme_language="en-us",
    phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
    print_step=25,
    print_eval=True,
    mixed_precision=False,
    output_path=output_path,
    datasets=[dataset_config],
)

# init audio processor
ap = AudioProcessor(**config.audio.to_dict())

# load training samples
train_samples, eval_samples = load_tts_samples(dataset_config, eval_split=True)

# init model
model = AlignTTS(config)

# init the trainer and 🚀
trainer = Trainer(
    TrainingArgs(),
    config,
    output_path,
    model=model,
    train_samples=train_samples,
    eval_samples=eval_samples,
    training_assets={"audio_processor": ap},
)
trainer.fit()