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
audio=audio_config,
batch_size=32,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=-1,
# 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,
precompute_num_workers=4,
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
text_cleaner="phoneme_cleaners",
use_phonemes=True,
phoneme_language="en-us",
# from TTS.tts.datasets.tokenizer import Tokenizer
output_path = os.path.dirname(os.path.abspath(__file__))
# init configs
dataset_config = BaseDatasetConfig(name="ljspeech",
meta_file_train="metadata.csv",
path=os.path.join(output_path,
"../LJSpeech-1.1/"))
audio_config = BaseAudioConfig(
sample_rate=22050,
do_trim_silence=True,
trim_db=60.0,
signal_norm=False,
mel_fmin=0.0,
mel_fmax=8000,
spec_gain=1.0,
log_func="np.log",
ref_level_db=20,
preemphasis=0.0,
)
config = Tacotron2Config( # This is the config that is saved for the future use
audio=audio_config,
batch_size=64,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=-1,
ga_alpha=5.0,
from TTS.config.shared_configs import BaseAudioConfig
from TTS.trainer import Trainer, TrainingArgs, init_training
from TTS.tts.configs import BaseDatasetConfig, VitsConfig
output_path = os.path.dirname(os.path.abspath(__file__))
dataset_config = BaseDatasetConfig(
name="ljspeech", meta_file_train="metadata.csv", path=os.path.join(output_path, "../LJSpeech-1.1/")
)
audio_config = BaseAudioConfig(
sample_rate=22050,
win_length=1024,
hop_length=256,
num_mels=80,
preemphasis=0.0,
ref_level_db=20,
log_func="np.log",
do_trim_silence=True,
trim_db=45,
mel_fmin=0,
mel_fmax=None,
spec_gain=1.0,
signal_norm=False,
do_amp_to_db_linear=False,
)
config = VitsConfig(
audio=audio_config,
run_name="vits_ljspeech",
batch_size=48,
eval_batch_size=16,
batch_group_size=5,
num_loader_workers=4,
num_eval_loader_workers=4,
from TTS.config.shared_configs import BaseAudioConfig
from TTS.speaker_encoder.speaker_encoder_config import SpeakerEncoderConfig
config_path = os.path.join(get_tests_output_path(), "test_model_config.json")
output_path = os.path.join(get_tests_output_path(), "train_outputs")
config = SpeakerEncoderConfig(
batch_size=4,
num_speakers_in_batch=1,
num_utters_per_speaker=10,
num_loader_workers=0,
max_train_step=2,
print_step=1,
save_step=1,
print_eval=True,
audio=BaseAudioConfig(num_mels=40),
)
config.audio.do_trim_silence = True
config.audio.trim_db = 60
config.save_json(config_path)
# train the model for one epoch
command_train = (
f"CUDA_VISIBLE_DEVICES='{get_device_id()}' python TTS/bin/train_encoder.py --config_path {config_path} "
f"--coqpit.output_path {output_path} "
"--coqpit.datasets.0.name ljspeech "
"--coqpit.datasets.0.meta_file_train metadata.csv "
"--coqpit.datasets.0.meta_file_val metadata.csv "
"--coqpit.datasets.0.path tests/data/ljspeech ")
run_cli(command_train)
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,
)
# Using the standard Capacitron config
capacitron_config = CapacitronVAEConfig(capacitron_VAE_loss_alpha=1.0)
config = TacotronConfig(
run_name="Blizzard-Capacitron-T1",
audio=audio_config,
capacitron_vae=capacitron_config,
use_capacitron_vae=True,