def accent_apply(base_dir: str, prep_name: str, text_name: str):
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
text_dir = get_text_dir(prep_dir, text_name, create=False)
if not os.path.isdir(text_dir):
print("Please add text first.")
else:
print("Applying accents...")
updated_sentences = infer_accents_apply(
sentences=load_text_csv(text_dir),
accented_symbols=_load_accents_csv(text_dir),
accent_ids=load_prep_accents_ids(prep_dir),
)
print("\n" + updated_sentences.get_formatted(
symbol_id_dict=load_text_symbol_converter(text_dir),
accent_id_dict=load_prep_accents_ids(prep_dir)))
_save_text_csv(text_dir, updated_sentences)
_check_for_unknown_symbols(base_dir, prep_name, text_name)
def convert_model(base_dir: str, prep_name: str, model_path: str,
custom_hparams: Optional[Dict[str, str]]):
prep_dir = get_prepared_dir(base_dir, prep_name)
convert_v1_to_v2_model(old_model_path=model_path,
custom_hparams=custom_hparams,
speakers=load_prep_speakers_json(prep_dir),
accents=load_prep_accents_ids(prep_dir),
symbols=load_prep_symbol_converter(prep_dir))
def get_infer_sentences(base_dir: str, prep_name: str,
text_name: str) -> InferSentenceList:
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
text_dir = get_text_dir(prep_dir, text_name, create=False)
if not os.path.isdir(text_dir):
print(f"The text '{text_name}' doesn't exist.")
assert False
result = InferSentenceList.from_sentences(
sentences=load_text_csv(text_dir),
accents=load_prep_accents_ids(prep_dir),
symbols=load_text_symbol_converter(text_dir))
return result
def _accent_template(base_dir: str, prep_name: str, text_name: str):
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
text_dir = get_text_dir(prep_dir, text_name, create=False)
if not os.path.isdir(text_dir):
print("Please add text first.")
else:
print("Updating accent template...")
accented_symbol_list = infer_accents_template(
sentences=load_text_csv(text_dir),
text_symbols=load_text_symbol_converter(text_dir),
accent_ids=load_prep_accents_ids(prep_dir),
)
_save_accents_csv(text_dir, accented_symbol_list)
def normalize_text(base_dir: str, prep_name: str, text_name: str):
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
text_dir = get_text_dir(prep_dir, text_name, create=False)
if not os.path.isdir(text_dir):
print("Please add text first.")
else:
print("Normalizing text...")
symbol_ids, updated_sentences = infer_norm(
sentences=load_text_csv(text_dir),
text_symbols=load_text_symbol_converter(text_dir))
print("\n" + updated_sentences.get_formatted(
symbol_id_dict=symbol_ids,
accent_id_dict=load_prep_accents_ids(prep_dir)))
_save_text_csv(text_dir, updated_sentences)
save_text_symbol_converter(text_dir, symbol_ids)
_accent_template(base_dir, prep_name, text_name)
_check_for_unknown_symbols(base_dir, prep_name, text_name)
def add_text(base_dir: str, prep_name: str, text_name: str, filepath: str,
lang: Language):
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
if not os.path.isdir(prep_dir):
print("Please prepare data first.")
else:
print("Adding text...")
symbol_ids, data = infer_add(
text=read_text(filepath),
lang=lang,
)
print(
"\n" +
data.get_formatted(symbol_id_dict=symbol_ids,
accent_id_dict=load_prep_accents_ids(prep_dir)))
text_dir = get_text_dir(prep_dir, text_name, create=True)
_save_text_csv(text_dir, data)
save_text_symbol_converter(text_dir, symbol_ids)
_accent_template(base_dir, prep_name, text_name)
_check_for_unknown_symbols(base_dir, prep_name, text_name)
def ipa_convert_text(base_dir: str,
prep_name: str,
text_name: str,
ignore_tones: bool = False,
ignore_arcs: bool = True):
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
text_dir = get_text_dir(prep_dir, text_name, create=False)
if not os.path.isdir(text_dir):
print("Please add text first.")
else:
print("Converting text to IPA...")
symbol_ids, updated_sentences = infer_convert_ipa(
sentences=load_text_csv(text_dir),
text_symbols=load_text_symbol_converter(text_dir),
ignore_tones=ignore_tones,
ignore_arcs=ignore_arcs)
print("\n" + updated_sentences.get_formatted(
symbol_id_dict=symbol_ids,
accent_id_dict=load_prep_accents_ids(prep_dir)))
_save_text_csv(text_dir, updated_sentences)
save_text_symbol_converter(text_dir, symbol_ids)
_accent_template(base_dir, prep_name, text_name)
_check_for_unknown_symbols(base_dir, prep_name, text_name)
def map_text(base_dir: str,
prep_name: str,
text_name: str,
symbols_map_path: str,
ignore_arcs: bool = True):
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
text_dir = get_text_dir(prep_dir, text_name, create=False)
if not os.path.isdir(text_dir):
print("Please add text first.")
else:
symbol_ids, updated_sentences = sents_map(
sentences=load_text_csv(text_dir),
text_symbols=load_text_symbol_converter(text_dir),
symbols_map=SymbolsMap.load(symbols_map_path),
ignore_arcs=ignore_arcs)
print("\n" + updated_sentences.get_formatted(
symbol_id_dict=symbol_ids,
accent_id_dict=load_prep_accents_ids(prep_dir)))
_save_text_csv(text_dir, updated_sentences)
save_text_symbol_converter(text_dir, symbol_ids)
_accent_template(base_dir, prep_name, text_name)
_check_for_unknown_symbols(base_dir, prep_name, text_name)
def eval_checkpoints_main(base_dir: str, train_name: str, select: int,
min_it: int, max_it: int):
train_dir = get_train_dir(base_dir, train_name, create=False)
assert os.path.isdir(train_dir)
prep_name = load_prep_name(train_dir)
prep_dir = get_prepared_dir(base_dir, prep_name)
symbols_conv = load_prep_symbol_converter(prep_dir)
speakers = load_prep_speakers_json(prep_dir)
accents = load_prep_accents_ids(prep_dir)
logger = prepare_logger()
eval_checkpoints(custom_hparams=None,
checkpoint_dir=get_checkpoints_dir(train_dir),
select=select,
min_it=min_it,
max_it=max_it,
n_symbols=len(symbols_conv),
n_speakers=len(speakers),
n_accents=len(accents),
valset=load_valset(train_dir),
logger=logger)
def train_main(base_dir: str,
train_name: str,
prep_name: str,
warm_start_train_name: Optional[str] = None,
warm_start_checkpoint: Optional[int] = None,
test_size: float = 0.01,
validation_size: float = 0.05,
custom_hparams: Optional[Dict[str, str]] = None,
split_seed: int = 1234,
weights_train_name: Optional[str] = None,
weights_checkpoint: Optional[int] = None,
use_weights_map: Optional[bool] = None,
map_from_speaker: Optional[str] = None):
prep_dir = get_prepared_dir(base_dir, prep_name)
train_dir = get_train_dir(base_dir, train_name, create=True)
logs_dir = get_train_logs_dir(train_dir)
taco_logger = Tacotron2Logger(logs_dir)
logger = prepare_logger(get_train_log_file(logs_dir), reset=True)
checkpoint_logger = prepare_logger(
log_file_path=get_train_checkpoints_log_file(logs_dir),
logger=logging.getLogger("checkpoint-logger"),
reset=True)
save_prep_name(train_dir, prep_name)
trainset, valset = split_dataset(prep_dir=prep_dir,
train_dir=train_dir,
test_size=test_size,
validation_size=validation_size,
split_seed=split_seed)
weights_model = try_load_checkpoint(base_dir=base_dir,
train_name=weights_train_name,
checkpoint=weights_checkpoint,
logger=logger)
weights_map = None
if use_weights_map is not None and use_weights_map:
weights_train_dir = get_train_dir(base_dir, weights_train_name, False)
weights_prep_name = load_prep_name(weights_train_dir)
weights_map = load_weights_map(prep_dir, weights_prep_name)
warm_model = try_load_checkpoint(base_dir=base_dir,
train_name=warm_start_train_name,
checkpoint=warm_start_checkpoint,
logger=logger)
save_callback = partial(
save_checkpoint,
save_checkpoint_dir=get_checkpoints_dir(train_dir),
logger=logger,
)
train(
custom_hparams=custom_hparams,
taco_logger=taco_logger,
symbols=load_prep_symbol_converter(prep_dir),
speakers=load_prep_speakers_json(prep_dir),
accents=load_prep_accents_ids(prep_dir),
trainset=trainset,
valset=valset,
save_callback=save_callback,
weights_map=weights_map,
weights_checkpoint=weights_model,
warm_model=warm_model,
map_from_speaker_name=map_from_speaker,
logger=logger,
checkpoint_logger=checkpoint_logger,
)