def get_all_symbols(prep_dir: str) -> Set[str]:
all_text_names = get_subfolder_names(prep_dir)
all_symbols: Set[str] = set()
for text_name in all_text_names:
text_dir = get_text_dir(prep_dir, text_name, create=False)
text_symbol_ids = load_text_symbol_converter(text_dir)
all_symbols |= text_symbol_ids.get_all_symbols()
return all_symbols
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 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 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)