from TTS.tts.utils.text.tokenizer import TTSTokenizer from TTS.utils.audio import AudioProcessor # set experiment paths output_path = os.path.dirname(os.path.abspath(__file__)) dataset_path = os.path.join(output_path, "../VCTK/") # download the dataset if not downloaded if not os.path.exists(dataset_path): from TTS.utils.downloaders import download_vctk download_vctk(dataset_path) # define dataset config dataset_config = BaseDatasetConfig(name="vctk", meta_file_train="", path=dataset_path) # define audio config # ❗ resample the dataset externally using `TTS/bin/resample.py` and set `resample=False` for faster training audio_config = BaseAudioConfig(sample_rate=22050, resample=True, do_trim_silence=True, trim_db=23.0) # define model config config = GlowTTSConfig( batch_size=64, eval_batch_size=16, num_loader_workers=4, num_eval_loader_workers=4,
import os from TTS.config.shared_configs import BaseAudioConfig from TTS.trainer import Trainer, TrainingArgs from TTS.tts.configs.shared_configs import BaseDatasetConfig from TTS.tts.configs.tacotron2_config import Tacotron2Config from TTS.tts.datasets import load_tts_samples from TTS.tts.models.tacotron2 import Tacotron2 from TTS.tts.utils.speakers import SpeakerManager from TTS.utils.audio import AudioProcessor output_path = os.path.dirname(os.path.abspath(__file__)) dataset_config = BaseDatasetConfig(name="vctk", meta_file_train="", path=os.path.join(output_path, "../VCTK/")) audio_config = BaseAudioConfig( sample_rate=22050, resample= False, # Resample to 22050 Hz. It slows down training. Use `TTS/bin/resample.py` to pre-resample and set this False for faster training. do_trim_silence=True, trim_db=23.0, signal_norm=False, mel_fmin=0.0, mel_fmax=8000, spec_gain=1.0, log_func="np.log", preemphasis=0.0, ) config = Tacotron2Config( # This is the config that is saved for the future use
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 from TTS.tts.datasets import load_tts_samples from TTS.tts.models.glow_tts import GlowTTS 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( name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/") ) # INITIALIZE THE TRAINING CONFIGURATION # Configure the model. Every config class inherits the BaseTTSConfig. config = GlowTTSConfig( batch_size=32, eval_batch_size=16, num_loader_workers=4, num_eval_loader_workers=4, run_eval=True, test_delay_epochs=-1, epochs=1000, text_cleaner="phoneme_cleaners", use_phonemes=True, phoneme_language="en-us",
OUTPATH = os.path.join(get_tests_output_path(), "loader_tests/") os.makedirs(OUTPATH, exist_ok=True) # create a dummy config for testing data loaders. c = BaseTTSConfig(text_cleaner="english_cleaners", num_loader_workers=0, batch_size=2, use_noise_augment=False) c.r = 5 c.data_path = "tests/data/ljspeech/" ok_ljspeech = os.path.exists(c.data_path) dataset_config = BaseDatasetConfig( name="ljspeech_test", # ljspeech_test to multi-speaker meta_file_train="metadata.csv", meta_file_val=None, path=c.data_path, language="en", ) DATA_EXIST = True if not os.path.exists(c.data_path): DATA_EXIST = False print(" > Dynamic data loader test: {}".format(DATA_EXIST)) class TestTTSDataset(unittest.TestCase): def __init__(self, *args, **kwargs): super().__init__(*args, **kwargs) self.max_loader_iter = 4
# BaseDatasetConfig: defines name, formatter and path of the dataset. from TTS.tts.configs.shared_configs import BaseDatasetConfig 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 from TTS.utils.downloaders import download_thorsten_de # 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( name="thorsten", meta_file_train="metadata.csv", path=os.path.join(output_path, "../thorsten-de/") ) # download dataset if not already present if not os.path.exists(dataset_config.path): print("Downloading dataset") download_thorsten_de(os.path.split(os.path.abspath(dataset_config.path))[0]) # INITIALIZE THE TRAINING CONFIGURATION # Configure the model. Every config class inherits the BaseTTSConfig. config = GlowTTSConfig( batch_size=32, eval_batch_size=16, num_loader_workers=4, num_eval_loader_workers=4, run_eval=True,
from TTS.config.shared_configs import BaseAudioConfig from TTS.tts.configs.shared_configs import BaseDatasetConfig, CapacitronVAEConfig from TTS.tts.configs.tacotron_config import TacotronConfig from TTS.tts.datasets import load_tts_samples from TTS.tts.models.tacotron import Tacotron from TTS.tts.utils.text.tokenizer import TTSTokenizer from TTS.utils.audio import AudioProcessor output_path = os.path.dirname(os.path.abspath(__file__)) data_path = "/srv/data/" # Using LJSpeech like dataset processing for the blizzard dataset dataset_config = BaseDatasetConfig(name="ljspeech", meta_file_train="metadata.csv", path=data_path) audio_config = BaseAudioConfig( sample_rate=24000, do_trim_silence=True, trim_db=60.0, signal_norm=True, mel_fmin=80.0, mel_fmax=12000, spec_gain=20.0, log_func="np.log10", ref_level_db=20, preemphasis=0.0, min_level_db=-100, )
from TTS.trainer import Trainer, TrainingArgs from TTS.tts.configs.shared_configs import BaseDatasetConfig from TTS.tts.configs.vits_config import VitsConfig from TTS.tts.datasets import load_tts_samples from TTS.tts.models.vits import Vits, VitsArgs from TTS.tts.utils.languages import LanguageManager from TTS.tts.utils.speakers import SpeakerManager from TTS.utils.audio import AudioProcessor output_path = os.path.dirname(os.path.abspath(__file__)) mailabs_path = "/home/julian/workspace/mailabs/**" dataset_paths = glob(mailabs_path) dataset_config = [ BaseDatasetConfig(name="mailabs", meta_file_train=None, path=path, language=path.split("/")[-1]) for path in dataset_paths ] audio_config = BaseAudioConfig( sample_rate=16000, win_length=1024, hop_length=256, num_mels=80, preemphasis=0.0, ref_level_db=20, log_func="np.log", do_trim_silence=False, trim_db=23.0, mel_fmin=0, mel_fmax=None,