def create_or_update_weights_map_main(base_dir: str,
prep_name: str,
weights_prep_name: str,
template_map: Optional[str] = None):
prep_dir = get_prepared_dir(base_dir, prep_name)
assert os.path.isdir(prep_dir)
orig_prep_dir = get_prepared_dir(base_dir, weights_prep_name)
assert os.path.isdir(orig_prep_dir)
logger = init_logger()
add_console_out_to_logger(logger)
logger.info(f"Creating/updating weights map for {weights_prep_name}...")
if template_map is not None:
_template_map = SymbolsMap.load(template_map)
else:
_template_map = None
if weights_map_exists(prep_dir, weights_prep_name):
existing_map = load_weights_map(prep_dir, weights_prep_name)
else:
existing_map = None
weights_map, symbols = create_or_update_weights_map(
orig=load_prep_symbol_converter(orig_prep_dir).get_all_symbols(),
dest=load_prep_symbol_converter(prep_dir).get_all_symbols(),
existing_map=existing_map,
template_map=_template_map,
)
save_weights_map(prep_dir, weights_prep_name, weights_map)
save_weights_symbols(prep_dir, weights_prep_name, symbols)
def create_or_update_inference_map_main(base_dir: str,
prep_name: str,
template_map: Optional[str] = None):
logger = init_logger()
add_console_out_to_logger(logger)
logger.info("Creating/updating inference map...")
prep_dir = get_prepared_dir(base_dir, prep_name)
assert os.path.isdir(prep_dir)
all_symbols = get_all_symbols(prep_dir)
if template_map is not None:
_template_map = SymbolsMap.load(template_map)
else:
_template_map = None
if infer_map_exists(prep_dir):
existing_map = load_infer_map(prep_dir)
else:
existing_map = None
infer_map, symbols = create_or_update_inference_map(
orig=load_prep_symbol_converter(prep_dir).get_all_symbols(),
dest=all_symbols,
existing_map=existing_map,
template_map=_template_map,
)
save_infer_map(prep_dir, infer_map)
save_infer_symbols(prep_dir, symbols)
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 _check_for_unknown_symbols(base_dir: str, prep_name: str, text_name: str):
infer_sents = get_infer_sentences(base_dir, prep_name, text_name)
prep_dir = get_prepared_dir(base_dir, prep_name, create=False)
logger = prepare_logger()
unknown_symbols_exist = infer_sents.replace_unknown_symbols(
model_symbols=load_prep_symbol_converter(prep_dir), logger=logger)
if unknown_symbols_exist:
logger.info(
"Some symbols are not in the prepared dataset symbolset. You need to create an inference map and then apply it to the symbols."
)
else:
logger.info(
"All symbols are in the prepared dataset symbolset. You can now synthesize this text."
)
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,
)