import os

from TTS.config.shared_configs import BaseAudioConfig
from TTS.trainer import Trainer, TrainingArgs
from TTS.tts.configs import BaseDatasetConfig, Tacotron2Config
from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.tacotron2 import Tacotron2
from TTS.utils.audio import AudioProcessor

# from TTS.tts.datasets.tokenizer import Tokenizer

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/")
)

audio_config = BaseAudioConfig(
    sample_rate=22050,
    do_trim_silence=True,
    trim_db=60.0,
    signal_norm=False,
    mel_fmin=0.0,
    mel_fmax=8000,
    spec_gain=1.0,
    log_func="np.log",
    ref_level_db=20,
    preemphasis=0.0,
)

config = Tacotron2Config(  # This is the config that is saved for the future use
    audio=audio_config,
    batch_size=64,
    eval_batch_size=16,
    num_loader_workers=4,
    num_eval_loader_workers=4,
    run_eval=True,
    test_delay_epochs=-1,
    ga_alpha=5.0,
    r=2,
    attention_type="dynamic_convolution",
    double_decoder_consistency=True,
    epochs=1000,
    text_cleaner="phoneme_cleaners",
    use_phonemes=True,
    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 = Tacotron2(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()