File size: 4,833 Bytes
11caf7d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 |
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()
|