tensorboard does not show steps in audio

[madey83]

i do VITS trainig from scrach and when i would like to hear test sentens on tensorboard i got 0 in steps count even if my learning steps is 250.

this is also was the problem when i done fine-tuning...

below my executed code:

import os
from glob import glob

from trainer import Trainer, TrainerArgs

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 CharactersConfig, Vits, VitsArgs, VitsAudioConfig
from TTS.tts.utils.languages import LanguageManager
from TTS.tts.utils.speakers import SpeakerManager
from TTS.tts.utils.text.tokenizer import TTSTokenizer
from TTS.utils.audio import AudioProcessor

def main():

#output_path = os.path.dirname(os.path.abspath(__file__))
output_path = "D:\\TTS-Training\\Vits-PL-Model-training\\Output"
dataset_config = BaseDatasetConfig(
	formatter="ljspeech", meta_file_train="metadata.csv", 
    #path="D:\\TTS-Training\\Vits-PL-Model-training\\dataLJSpeech_final"
    path="D:\\TTS-Training\\LJSpeech-1.1"
)
audio_config = VitsAudioConfig(
	sample_rate=22050, win_length=1024, hop_length=256, num_mels=80, mel_fmin=0, mel_fmax=None
)
    
config = VitsConfig(
	audio=audio_config,
	run_name="Vits-TTS-PL",
	batch_size=16,
	eval_batch_size=8,
	batch_group_size=5,
	num_loader_workers=4,
	num_eval_loader_workers=2,
	run_eval=True,
	test_delay_epochs=-1,
	epochs=1000,
    save_step=1000,
    save_checkpoints=True,
    save_n_checkpoints=2,
    save_best_after=5000,
    add_blank=True,                      
	text_cleaner="multilingual_cleaners",
	use_phonemes=True,
	phoneme_language="pl",
	phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
	compute_input_seq_cache=True,
	print_step=25,
	print_eval=True,
	mixed_precision=False,
	output_path=output_path,
	datasets=[dataset_config],
	cudnn_benchmark=False,
	test_sentences=[
        "Nazywam się Rusty Sabich i jestem prokuratorem w tym procesie.",
        "Jeśli uznacie to za bardzo prawdopodobne, musicie wypuścić LEDU 20 października 1963 roku.",
	],
)

# 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.
# config is updated with the default characters if not defined in 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,
)

# init model
model = Vits(config, ap, tokenizer, speaker_manager=None)

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

from multiprocessing import Process, freeze_support
if name == 'main':
freeze_support() # needed for Windows
main()

any suggestion

[eginhard]

Let it run for some time, it should show more outputs eventually and you can scroll through different steps then.

[madey83]

thanks for answer, but first time when i star traing i have got from fist step audio available...

when i have reinstall windows this does not show any more even if i move to 1000 steps...