Rename converted to wavs for TTS training format. Add script to repeat metadata.csv column for ljspeech format.
Paul Pham
3 years ago
parent
e61dccf52e
commit
733afa7f45
@ -0,0 +1,23 @@
|
|||||||
|
import pyjson5
|
||||||
|
import os
|
||||||
|
|
||||||
|
CUR_DIR = os.getcwd()
|
||||||
|
|
||||||
|
with open("./example-config.json") as input_f:
|
||||||
|
with open("./config.json", "w") as output_f:
|
||||||
|
lines = input_f.readlines()
|
||||||
|
data = ''.join(lines)
|
||||||
|
obj = pyjson5.loads(data)
|
||||||
|
|
||||||
|
audio = obj["audio"]
|
||||||
|
audio["stats_path"] = os.path.join(CUR_DIR, 'scale_stats.npy' )
|
||||||
|
|
||||||
|
#output_path = obj['output_path']
|
||||||
|
obj["output_path"] = os.path.join(CUR_DIR, 'models', 'LJSpeech')
|
||||||
|
|
||||||
|
#phoneme_path = obj['phoneme_cache_path']
|
||||||
|
obj["phoneme_cache_path"] = os.path.join(CUR_DIR, 'models', 'phoneme_cache')
|
||||||
|
|
||||||
|
obj["datasets"][0]["path"] = os.path.join(CUR_DIR)
|
||||||
|
|
||||||
|
output_f.write(pyjson5.dumps(obj))
|
||||||
@ -0,0 +1,15 @@
|
|||||||
|
import os
|
||||||
|
|
||||||
|
CUR_DIR = os.getcwd()
|
||||||
|
|
||||||
|
with open("./example-metadata.csv") as input_f:
|
||||||
|
with open("./metadata.csv", "w") as output_f:
|
||||||
|
lines = input_f.readlines()
|
||||||
|
write_lines = []
|
||||||
|
|
||||||
|
for line in lines:
|
||||||
|
cols = line.split('|')
|
||||||
|
cols.append(cols[1]) # repeat col[1] to be col[2] for the ljspeech format
|
||||||
|
write_lines.append('|'.join(cols))
|
||||||
|
|
||||||
|
output_f.write('\n'.join(write_lines))
|
||||||
@ -0,0 +1,2 @@
|
|||||||
|
TTS
|
||||||
|
pyjson5
|
||||||
@ -0,0 +1,106 @@
|
|||||||
|
import os
|
||||||
|
|
||||||
|
from trainer import Trainer, TrainerArgs
|
||||||
|
|
||||||
|
from TTS.config.shared_configs import BaseAudioConfig
|
||||||
|
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.text.tokenizer import TTSTokenizer
|
||||||
|
from TTS.utils.audio import AudioProcessor
|
||||||
|
|
||||||
|
# from TTS.tts.datasets.tokenizer import Tokenizer
|
||||||
|
|
||||||
|
output_path = "."
|
||||||
|
|
||||||
|
# init configs
|
||||||
|
dataset_config = BaseDatasetConfig(
|
||||||
|
formatter="mailabs",
|
||||||
|
dataset_name="ljspeech", meta_file_train="metadata.csv",
|
||||||
|
path=output_path # os.path.join(output_path, "/content/LJSpeech-1.1")
|
||||||
|
)
|
||||||
|
|
||||||
|
print(str(dataset_config))
|
||||||
|
|
||||||
|
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=0.0,
|
||||||
|
decoder_loss_alpha=0.25,
|
||||||
|
postnet_loss_alpha=0.25,
|
||||||
|
postnet_diff_spec_alpha=0,
|
||||||
|
decoder_diff_spec_alpha=0,
|
||||||
|
decoder_ssim_alpha=0,
|
||||||
|
postnet_ssim_alpha=0,
|
||||||
|
r=2,
|
||||||
|
attention_type="dynamic_convolution",
|
||||||
|
double_decoder_consistency=False,
|
||||||
|
epochs=1000,
|
||||||
|
text_cleaner="phoneme_cleaners",
|
||||||
|
use_phonemes=True,
|
||||||
|
phoneme_language="en-us",
|
||||||
|
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
|
||||||
|
print_step=25,
|
||||||
|
print_eval=True,
|
||||||
|
mixed_precision=False,
|
||||||
|
output_path=output_path,
|
||||||
|
datasets=[dataset_config],
|
||||||
|
)
|
||||||
|
|
||||||
|
# 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,
|
||||||
|
)
|
||||||
|
|
||||||
|
# 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)
|
||||||
|
|
||||||
|
# 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()
|
||||||
|
|
||||||
Loading…
Reference in new issue