def text_to_sequence(text, cleaner_names, tp=None):
'''Converts a string of text to a sequence of IDs corresponding to the symbols in the text.
The text can optionally have ARPAbet sequences enclosed in curly braces embedded
in it. For example, "Turn left on {HH AW1 S S T AH0 N} Street."
Args:
text: string to convert to a sequence
cleaner_names: names of the cleaner functions to run the text through
Returns:
List of integers corresponding to the symbols in the text
'''
# pylint: disable=global-statement
global _symbol_to_id
if tp:
_symbols, _ = make_symbols(**tp)
_symbol_to_id = {s: i for i, s in enumerate(_symbols)}
sequence = []
# Check for curly braces and treat their contents as ARPAbet:
while text:
m = _CURLY_RE.match(text)
if not m:
sequence += _symbols_to_sequence(_clean_text(text, cleaner_names))
break
sequence += _symbols_to_sequence(_clean_text(m.group(1),
cleaner_names))
sequence += _arpabet_to_sequence(m.group(2))
text = m.group(3)
return sequence
def pad_with_eos_bos(phoneme_sequence, tp=None):
# pylint: disable=global-statement
global _phonemes_to_id, _bos, _eos
if tp:
_bos = tp['bos']
_eos = tp['eos']
_, _phonemes = make_symbols(**tp)
_phonemes_to_id = {s: i for i, s in enumerate(_phonemes)}
return [_phonemes_to_id[_bos]
] + list(phoneme_sequence) + [_phonemes_to_id[_eos]]
def _create_random_model(self):
# pylint: disable=global-statement
global symbols, phonemes
config = load_config(
os.path.join(get_tests_output_path(), 'dummy_model_config.json'))
if 'characters' in config.keys():
symbols, phonemes = make_symbols(**config.characters)
num_chars = len(phonemes) if config.use_phonemes else len(symbols)
model = setup_model(num_chars, 0, config)
output_path = os.path.join(get_tests_output_path())
save_checkpoint(model, None, 10, 10, 1, output_path)
def sequence_to_phoneme(sequence, tp=None):
# pylint: disable=global-statement
'''Converts a sequence of IDs back to a string'''
global _id_to_phonemes
result = ''
if tp:
_, _phonemes = make_symbols(**tp)
_id_to_phonemes = {i: s for i, s in enumerate(_phonemes)}
for symbol_id in sequence:
if symbol_id in _id_to_phonemes:
s = _id_to_phonemes[symbol_id]
result += s
return result.replace('}{', ' ')
def sequence_to_text(sequence, tp=None):
'''Converts a sequence of IDs back to a string'''
# pylint: disable=global-statement
global _id_to_symbol
if tp:
_symbols, _ = make_symbols(**tp)
_id_to_symbol = {i: s for i, s in enumerate(_symbols)}
result = ''
for symbol_id in sequence:
if symbol_id in _id_to_symbol:
s = _id_to_symbol[symbol_id]
# Enclose ARPAbet back in curly braces:
if len(s) > 1 and s[0] == '@':
s = '{%s}' % s[1:]
result += s
return result.replace('}{', ' ')
def phoneme_to_sequence(text,
cleaner_names,
language,
enable_eos_bos=False,
tp=None):
# pylint: disable=global-statement
global _phonemes_to_id
if tp:
_, _phonemes = make_symbols(**tp)
_phonemes_to_id = {s: i for i, s in enumerate(_phonemes)}
sequence = []
clean_text = _clean_text(text, cleaner_names)
to_phonemes = text2phone(clean_text, language)
if to_phonemes is None:
print("!! After phoneme conversion the result is None. -- {} ".format(
clean_text))
# iterate by skipping empty strings - NOTE: might be useful to keep it to have a better intonation.
for phoneme in filter(None, to_phonemes.split('|')):
sequence += _phoneme_to_sequence(phoneme)
# Append EOS char
if enable_eos_bos:
sequence = pad_with_eos_bos(sequence, tp=tp)
return sequence
'--gst_style',
help="Wav path file for GST stylereference.",
default=None)
args = parser.parse_args()
# load the config
C = load_config(args.config_path)
C.forward_attn_mask = True
# load the audio processor
ap = AudioProcessor(**C.audio)
# if the vocabulary was passed, replace the default
if 'characters' in C.keys():
symbols, phonemes = make_symbols(**C.characters)
speaker_embedding = None
speaker_embedding_dim = None
num_speakers = 0
# load speakers
if args.speakers_json != '':
speaker_mapping = json.load(open(args.speakers_json, 'r'))
num_speakers = len(speaker_mapping)
if C.use_external_speaker_embedding_file:
if args.speaker_fileid is not None:
speaker_embedding = speaker_mapping[args.speaker_fileid]['embedding']
else: # if speaker_fileid is not specificated use the first sample in speakers.json
speaker_embedding = speaker_mapping[list(speaker_mapping.keys())[0]]['embedding']
speaker_embedding_dim = len(speaker_embedding)
def main(args): # pylint: disable=redefined-outer-name
# pylint: disable=global-variable-undefined
global meta_data_train, meta_data_eval, symbols, phonemes
# Audio processor
ap = AudioProcessor(**c.audio)
if 'characters' in c.keys():
symbols, phonemes = make_symbols(**c.characters)
# DISTRUBUTED
if num_gpus > 1:
init_distributed(args.rank, num_gpus, args.group_id,
c.distributed["backend"], c.distributed["url"])
num_chars = len(phonemes) if c.use_phonemes else len(symbols)
# load data instances
meta_data_train, meta_data_eval = load_meta_data(c.datasets)
# set the portion of the data used for training
if 'train_portion' in c.keys():
meta_data_train = meta_data_train[:int(len(meta_data_train) * c.train_portion)]
if 'eval_portion' in c.keys():
meta_data_eval = meta_data_eval[:int(len(meta_data_eval) * c.eval_portion)]
# parse speakers
if c.use_speaker_embedding:
speakers = get_speakers(meta_data_train)
if args.restore_path:
if c.use_external_speaker_embedding_file: # if restore checkpoint and use External Embedding file
prev_out_path = os.path.dirname(args.restore_path)
speaker_mapping = load_speaker_mapping(prev_out_path)
if not speaker_mapping:
print("WARNING: speakers.json was not found in restore_path, trying to use CONFIG.external_speaker_embedding_file")
speaker_mapping = load_speaker_mapping(c.external_speaker_embedding_file)
if not speaker_mapping:
raise RuntimeError("You must copy the file speakers.json to restore_path, or set a valid file in CONFIG.external_speaker_embedding_file")
speaker_embedding_dim = len(speaker_mapping[list(speaker_mapping.keys())[0]]['embedding'])
elif not c.use_external_speaker_embedding_file: # if restore checkpoint and don't use External Embedding file
prev_out_path = os.path.dirname(args.restore_path)
speaker_mapping = load_speaker_mapping(prev_out_path)
speaker_embedding_dim = None
assert all([speaker in speaker_mapping
for speaker in speakers]), "As of now you, you cannot " \
"introduce new speakers to " \
"a previously trained model."
elif c.use_external_speaker_embedding_file and c.external_speaker_embedding_file: # if start new train using External Embedding file
speaker_mapping = load_speaker_mapping(c.external_speaker_embedding_file)
speaker_embedding_dim = len(speaker_mapping[list(speaker_mapping.keys())[0]]['embedding'])
elif c.use_external_speaker_embedding_file and not c.external_speaker_embedding_file: # if start new train using External Embedding file and don't pass external embedding file
raise "use_external_speaker_embedding_file is True, so you need pass a external speaker embedding file, run GE2E-Speaker_Encoder-ExtractSpeakerEmbeddings-by-sample.ipynb or AngularPrototypical-Speaker_Encoder-ExtractSpeakerEmbeddings-by-sample.ipynb notebook in notebooks/ folder"
else: # if start new train and don't use External Embedding file
speaker_mapping = {name: i for i, name in enumerate(speakers)}
speaker_embedding_dim = None
save_speaker_mapping(OUT_PATH, speaker_mapping)
num_speakers = len(speaker_mapping)
print("Training with {} speakers: {}".format(num_speakers,
", ".join(speakers)))
else:
num_speakers = 0
speaker_embedding_dim = None
speaker_mapping = None
model = setup_model(num_chars, num_speakers, c, speaker_embedding_dim)
params = set_weight_decay(model, c.wd)
optimizer = RAdam(params, lr=c.lr, weight_decay=0)
if c.stopnet and c.separate_stopnet:
optimizer_st = RAdam(model.decoder.stopnet.parameters(),
lr=c.lr,
weight_decay=0)
else:
optimizer_st = None
if c.apex_amp_level == "O1":
# pylint: disable=import-outside-toplevel
from apex import amp
model.cuda()
model, optimizer = amp.initialize(model, optimizer, opt_level=c.apex_amp_level)
else:
amp = None
# setup criterion
criterion = TacotronLoss(c, stopnet_pos_weight=10.0, ga_sigma=0.4)
if args.restore_path:
checkpoint = torch.load(args.restore_path, map_location='cpu')
try:
# TODO: fix optimizer init, model.cuda() needs to be called before
# optimizer restore
# optimizer.load_state_dict(checkpoint['optimizer'])
if c.reinit_layers:
raise RuntimeError
model.load_state_dict(checkpoint['model'])
except KeyError:
print(" > Partial model initialization.")
model_dict = model.state_dict()
model_dict = set_init_dict(model_dict, checkpoint['model'], c)
# torch.save(model_dict, os.path.join(OUT_PATH, 'state_dict.pt'))
# print("State Dict saved for debug in: ", os.path.join(OUT_PATH, 'state_dict.pt'))
model.load_state_dict(model_dict)
del model_dict
if amp and 'amp' in checkpoint:
amp.load_state_dict(checkpoint['amp'])
for group in optimizer.param_groups:
group['lr'] = c.lr
print(" > Model restored from step %d" % checkpoint['step'],
flush=True)
args.restore_step = checkpoint['step']
else:
args.restore_step = 0
if use_cuda:
model.cuda()
criterion.cuda()
# DISTRUBUTED
if num_gpus > 1:
model = apply_gradient_allreduce(model)
if c.noam_schedule:
scheduler = NoamLR(optimizer,
warmup_steps=c.warmup_steps,
last_epoch=args.restore_step - 1)
else:
scheduler = None
num_params = count_parameters(model)
print("\n > Model has {} parameters".format(num_params), flush=True)
if 'best_loss' not in locals():
best_loss = float('inf')
global_step = args.restore_step
for epoch in range(0, c.epochs):
c_logger.print_epoch_start(epoch, c.epochs)
# set gradual training
if c.gradual_training is not None:
r, c.batch_size = gradual_training_scheduler(global_step, c)
c.r = r
model.decoder.set_r(r)
if c.bidirectional_decoder:
model.decoder_backward.set_r(r)
print("\n > Number of output frames:", model.decoder.r)
train_avg_loss_dict, global_step = train(model, criterion, optimizer,
optimizer_st, scheduler, ap,
global_step, epoch, amp, speaker_mapping)
eval_avg_loss_dict = evaluate(model, criterion, ap, global_step, epoch, speaker_mapping)
c_logger.print_epoch_end(epoch, eval_avg_loss_dict)
target_loss = train_avg_loss_dict['avg_postnet_loss']
if c.run_eval:
target_loss = eval_avg_loss_dict['avg_postnet_loss']
best_loss = save_best_model(target_loss, best_loss, model, optimizer, global_step, epoch, c.r,
OUT_PATH, amp_state_dict=amp.state_dict() if amp else None)