train_tacotron2.py

import os

# Trainer: Where the ✨️ happens.
# TrainingArgs: Defines the set of arguments of the Trainer.
from trainer import Trainer, TrainerArgs

# GlowTTSConfig: all model related values for training, validating and testing.
# from TTS.tts.configs.glow_tts_config import GlowTTSConfig
from TTS.tts.configs.tacotron2_config import Tacotron2Config


# BaseDatasetConfig: defines name, formatter and path of the dataset.
from TTS.tts.configs.shared_configs import BaseDatasetConfig , CharactersConfig
from TTS.config.shared_configs import BaseAudioConfig
from TTS.tts.datasets import load_tts_samples


# from TTS.tts.models.glow_tts import GlowTTS
from TTS.tts.models.tacotron2 import Tacotron2


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

# 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="mozilla", meta_file_train="metadata.csv", path="/kaggle/input/persian-tts-dataset-famale" 
)

audio_config = BaseAudioConfig(
    sample_rate=24000,
    do_trim_silence=True,
    resample=False
    
)

character_config=CharactersConfig(
  characters='ءابتثجحخدذرزسشصضطظعغفقلمنهويِپچژکگیآأؤإئًَُّ',
  punctuations='!(),-.:;? ̠،؛؟‌<>',
  phonemes='ˈˌːˑpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟaegiouwyɪʊ̩æɑɔəɚɛɝɨ̃ʉʌʍ0123456789"#$%*+/=ABCDEFGHIJKLMNOPRSTUVWXYZ[]^_{}',
  pad="<PAD>",
  eos="<EOS>",
  bos="<BOS>",
  blank="<BLNK>",
  characters_class="TTS.tts.utils.text.characters.IPAPhonemes",
  )
# INITIALIZE THE TRAINING CONFIGURATION
# Configure the model. Every config class inherits the BaseTTSConfig.
config = Tacotron2Config(
    save_step=1000,
    batch_size=8,#
    eval_batch_size=4,#
    model='tacotron2',
    num_loader_workers=0,
    num_eval_loader_workers=0,
    output_path=output_path,
    audio=audio_config,
    use_phonemes=True,
    phoneme_language="fa",
    text_cleaner="basic_cleaners",
    phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
    characters=character_config,
    print_step=25,
    print_eval=False,
    mixed_precision=True,
    datasets=[dataset_config],
    test_sentences=[
        "سلطان محمود در زمستانی سخت به طلخک گفت که: با این جامه ی یک لا در این سرما چه می کنی ",
        "مردی نزد بقالی آمد و گفت پیاز هم ده تا دهان بدان خو شبوی سازم.",
        "از مال خود پاره ای گوشت بستان و زیره بایی معطّر بساز",
        "یک بار هم از جهنم بگویید.",
        "یکی اسبی به عاریت خواست"
    ],
    num_chars=len('ˈˌːˑpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟaegiouwyɪʊ̩æɑɔəɚɛɝɨ̃ʉʌʍ0123456789"#$%*+/=ABCDEFGHIJKLMNOPRSTUVWXYZ[]^_{}'),
    
)

# 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,
    eval_split_size=config.eval_split_size,
    #formatter=changizer
)

# 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 = Tacotron2(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.
trainer = Trainer(
    TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples
)

# AND... 3,2,1... 🚀
trainer.fit()