train_vits.py

import os

from trainer import Trainer, TrainerArgs

from TTS.tts.configs.shared_configs import BaseDatasetConfig , CharactersConfig
from TTS.tts.configs.vits_config import VitsConfig
from TTS.tts.datasets import load_tts_samples
from TTS.tts.models.vits import Vits, VitsAudioConfig
from TTS.tts.utils.text.tokenizer import TTSTokenizer
from TTS.utils.audio import AudioProcessor

output_path = os.path.dirname(os.path.abspath(__file__))
# DEFINE DATASET CONFIG
TRAIN_PATH = "/home/aymen/Tamazight-NLP/Speech/media_ipsapps/shi_tls/cut_22kHz_offset/manifests/"
dataset_config = BaseDatasetConfig(
    formatter="nemo", meta_file_train="manifest_processed.json", path=TRAIN_PATH
)

audio_config = VitsAudioConfig(
    sample_rate=22050, win_length=1024, hop_length=256, num_mels=80, mel_fmin=0, mel_fmax=None
)

character_config = CharactersConfig(
    characters_class= "TTS.tts.models.vits.VitsCharacters",
    characters= "ⴰⴱⴳⴷⴹⴻⴼⴽⵀⵃⵄⵅⵇⵉⵊⵍⵎⵏⵓⵔⵕⵖⵙⵚⵛⵜⵟⵡⵢⵣⵥⵯ",
    punctuations=" !,.:?",
    pad= "<PAD>",
    eos= "<EOS>",
    bos= "<BOS>",
    blank= "<BLNK>",
)

config = VitsConfig(
    audio=audio_config,
    characters=character_config,
    run_name="vits_shi_male",
    batch_size=16,
    eval_batch_size=4,
    batch_group_size=5,
    num_loader_workers=4,
    num_eval_loader_workers=4,
    run_eval=True,
    test_delay_epochs=-1,
    epochs=1000,
    save_step=5000,
    text_cleaner="no_cleaners",
    use_phonemes=False,
    compute_input_seq_cache=True,
    print_step=25,
    print_eval=True,
    mixed_precision=True,
    output_path=output_path,
    datasets=[dataset_config],
    cudnn_benchmark=False,
    test_sentences=[
        ["ⴰⵣⵓⵍ. ⵎⴰⵏⵣⴰⴽⵉⵏ?"],
        ["ⵡⴰ ⵜⴰⵎⵖⴰⵔⵜ ⵎⴰ ⴷ ⵓⴽⴰⵏ ⵜⵙⴽⵔⵜ?"],
        ["ⴳⵏ! ⴰⴷ ⴰⴽ ⵉⵙⵙⴳⵏ ⵕⴱⴱⵉ ⵉⵜⵜⵓ ⴽ."],
        ["ⴰⵔⵔⴰⵡ ⵏ ⵍⵀⵎⵎ ⵢⵓⴽⵔ ⴰⵖ ⵉⵀⴷⵓⵎⵏ ⵏⵏⵖ!"]
    ],
)

# 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.
# config is updated with the default characters if not defined in 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,
    eval_split_size=config.eval_split_size,
)

# init model
model = Vits(config, ap, tokenizer, speaker_manager=None)

# init the trainer and 🚀
trainer = Trainer(
    TrainerArgs(),
    config,
    output_path,
    model=model,
    train_samples=train_samples,
    eval_samples=eval_samples,
)
trainer.fit()