)
config = SpeedySpeechConfig(
run_name="fast_pitch_ljspeech",
audio=audio_config,
batch_size=32,
eval_batch_size=16,
num_loader_workers=8,
num_eval_loader_workers=4,
compute_input_seq_cache=True,
compute_f0=True,
f0_cache_path=os.path.join(output_path, "f0_cache"),
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
text_cleaner="english_cleaners",
use_phonemes=True,
use_espeak_phonemes=False,
phoneme_language="en-us",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
print_step=50,
print_eval=False,
mixed_precision=False,
sort_by_audio_len=True,
max_seq_len=500000,
output_path=output_path,
datasets=[dataset_config],
use_speaker_embedding=True,
)
# init audio processor
config = SpeedySpeechConfig(
run_name="speedy_speech_thorsten-de",
audio=audio_config,
batch_size=32,
eval_batch_size=16,
num_loader_workers=4,
num_eval_loader_workers=4,
compute_input_seq_cache=True,
run_eval=True,
test_delay_epochs=-1,
epochs=1000,
min_audio_len=11050, # need to up min_audio_len to avois speedy speech error
text_cleaner="phoneme_cleaners",
use_phonemes=True,
phoneme_language="de",
phoneme_cache_path=os.path.join(output_path, "phoneme_cache"),
precompute_num_workers=4,
print_step=50,
print_eval=False,
mixed_precision=False,
test_sentences=[
"Es hat mich viel Zeit gekostet ein Stimme zu entwickeln, jetzt wo ich sie habe werde ich nicht mehr schweigen.",
"Sei eine Stimme, kein Echo.",
"Es tut mir Leid David. Das kann ich leider nicht machen.",
"Dieser Kuchen ist großartig. Er ist so lecker und feucht.",
"Vor dem 22. November 1963.",
],
sort_by_audio_len=True,
max_seq_len=500000,
output_path=output_path,
datasets=[dataset_config],
)
from tests import get_device_id, get_tests_output_path, run_cli
from TTS.tts.configs.speedy_speech_config import SpeedySpeechConfig
config_path = os.path.join(get_tests_output_path(),
"test_speedy_speech_config.json")
output_path = os.path.join(get_tests_output_path(), "train_outputs")
config = SpeedySpeechConfig(
batch_size=8,
eval_batch_size=8,
num_loader_workers=0,
num_eval_loader_workers=0,
text_cleaner="english_cleaners",
use_phonemes=True,
phoneme_language="en-us",
phoneme_cache_path="tests/data/ljspeech/phoneme_cache/",
run_eval=True,
test_delay_epochs=-1,
epochs=1,
print_step=1,
print_eval=True,
test_sentences=[
"Be a voice, not an echo.",
],
)
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_tts.py --config_path {config_path} "