from TTS.vocoder.configs import MultibandMelganConfig
from TTS.vocoder.datasets.preprocess import load_wav_data
from TTS.vocoder.models.gan import GAN
output_path = os.path.dirname(os.path.abspath(__file__))
config = MultibandMelganConfig(
batch_size=32,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
run_eval=True,
test_delay_epochs=5,
epochs=1000,
seq_len=8192,
pad_short=2000,
use_noise_augment=True,
eval_split_size=10,
print_step=25,
print_eval=False,
mixed_precision=False,
lr_gen=1e-4,
lr_disc=1e-4,
data_path=os.path.join(output_path, "../LJSpeech-1.1/wavs/"),
output_path=output_path,
)
# init audio processor
ap = AudioProcessor(**config.audio.to_dict())
# load training samples
eval_samples, train_samples = load_wav_data(config.data_path,
from tests import get_device_id, get_tests_output_path, run_cli
from TTS.vocoder.configs import MultibandMelganConfig
config_path = os.path.join(get_tests_output_path(), "test_vocoder_config.json")
output_path = os.path.join(get_tests_output_path(), "train_outputs")
config = MultibandMelganConfig(
batch_size=8,
eval_batch_size=8,
num_loader_workers=0,
num_eval_loader_workers=0,
run_eval=True,
test_delay_epochs=-1,
epochs=1,
seq_len=8192,
eval_split_size=1,
print_step=1,
print_eval=True,
data_path="tests/data/ljspeech",
discriminator_model_params={
"base_channels": 16,
"max_channels": 64,
"downsample_factors": [4, 4, 4]
},
output_path=output_path,
)
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_vocoder.py --config_path {config_path} "
import shutil
from tests import get_device_id, get_tests_output_path, run_cli
from TTS.vocoder.configs import MultibandMelganConfig
config_path = os.path.join(get_tests_output_path(), "test_vocoder_config.json")
output_path = os.path.join(get_tests_output_path(), "train_outputs")
config = MultibandMelganConfig(
batch_size=8,
eval_batch_size=8,
num_loader_workers=0,
num_val_loader_workers=0,
run_eval=True,
test_delay_epochs=-1,
epochs=1,
seq_len=8192,
eval_split_size=1,
print_step=1,
print_eval=True,
data_path="tests/data/ljspeech",
output_path=output_path,
)
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_vocoder_gan.py --config_path {config_path} "
)