Upload train_tacotron2.py with huggingface_hub

train_tacotron2.py

@@ -0,0 +1,122 @@
+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()