File size: 1,180 Bytes
45ee559
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import os

from trainer import Trainer, TrainerArgs

from TTS.utils.audio import AudioProcessor
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, config.eval_split_size)

# init model
model = GAN(config, ap)

# init the trainer and 🚀
trainer = Trainer(
    TrainerArgs(), config, output_path, model=model, train_samples=train_samples, eval_samples=eval_samples
)
trainer.fit()