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 # 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.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" ) audio_config = BaseAudioConfig( sample_rate=22050, do_trim_silence=True, resample=False ) character_config=CharactersConfig( characters='ءابتثجحخدذرزسشصضطظعغفقلمنهويِپچژکگیآأؤإئًَُّ', punctuations='!(),-.:;? ̠،؛؟‌<>', phonemes='ˈˌːˑpbtdʈɖcɟkɡqɢʔɴŋɲɳnɱmʙrʀⱱɾɽɸβfvθðszʃʒʂʐçʝxɣχʁħʕhɦɬɮʋɹɻjɰlɭʎʟaegiouwyɪʊ̩æɑɔəɚɛɝɨ̃ʉʌʍ0123456789"#$%*+/=ABCDEFGHIJKLMNOPRSTUVWXYZ[]^_{}', pad="", eos="", bos="", blank="", characters_class="TTS.tts.utils.text.characters.IPAPhonemes", ) # INITIALIZE THE TRAINING CONFIGURATION # Configure the model. Every config class inherits the BaseTTSConfig. config = GlowTTSConfig( batch_size=8,#batch_size=32, eval_batch_size=4,#eval_batch_size=16, num_loader_workers=0, num_eval_loader_workers=0, run_eval=True, test_delay_epochs=-1, epochs=1000, save_step=1000, text_cleaner="basic_cleaners", use_phonemes=True, phoneme_language="fa", phoneme_cache_path=os.path.join(output_path, "phoneme_cache"), characters=character_config, print_step=25, print_eval=False, mixed_precision=True, output_path=output_path, datasets=[dataset_config], audio=audio_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" ], ) # 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 = GlowTTS(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()