def format_data(data):
if c.use_speaker_embedding:
speaker_mapping = load_speaker_mapping(OUT_PATH)
# setup input data
text_input = data[0]
text_lengths = data[1]
speaker_names = data[2]
mel_input = data[4].permute(0, 2, 1) # B x D x T
mel_lengths = data[5]
attn_mask = data[8]
avg_text_length = torch.mean(text_lengths.float())
avg_spec_length = torch.mean(mel_lengths.float())
if c.use_speaker_embedding:
speaker_ids = [
speaker_mapping[speaker_name] for speaker_name in speaker_names
]
speaker_ids = torch.LongTensor(speaker_ids)
else:
speaker_ids = None
# dispatch data to GPU
if use_cuda:
text_input = text_input.cuda(non_blocking=True)
text_lengths = text_lengths.cuda(non_blocking=True)
mel_input = mel_input.cuda(non_blocking=True)
mel_lengths = mel_lengths.cuda(non_blocking=True)
if speaker_ids is not None:
speaker_ids = speaker_ids.cuda(non_blocking=True)
if attn_mask is not None:
attn_mask = attn_mask.cuda(non_blocking=True)
return text_input, text_lengths, mel_input, mel_lengths, speaker_ids,\
avg_text_length, avg_spec_length, attn_mask
def load_speakers(self):
# load speakers
if self.model_config.use_speaker_embedding is not None:
self.tts_speakers = load_speaker_mapping(self.tts_config.tts_speakers_json)
self.num_speakers = len(self.tts_speakers)
else:
self.num_speakers = 0
# set external speaker embedding
if self.tts_config.use_external_speaker_embedding_file:
speaker_embedding = self.tts_speakers[list(self.tts_speakers.keys())[0]]['embedding']
self.speaker_embedding_dim = len(speaker_embedding)
def format_data(data, speaker_mapping=None):
if speaker_mapping is None and c.use_speaker_embedding and not c.use_external_speaker_embedding_file:
speaker_mapping = load_speaker_mapping(OUT_PATH)
# setup input data
text_input = data[0]
text_lengths = data[1]
speaker_names = data[2]
linear_input = data[3] if c.model in ["Tacotron"] else None
mel_input = data[4]
mel_lengths = data[5]
stop_targets = data[6]
avg_text_length = torch.mean(text_lengths.float())
avg_spec_length = torch.mean(mel_lengths.float())
if c.use_speaker_embedding:
if c.use_external_speaker_embedding_file:
speaker_embeddings = data[8]
speaker_ids = None
else:
speaker_ids = [
speaker_mapping[speaker_name] for speaker_name in speaker_names
]
speaker_ids = torch.LongTensor(speaker_ids)
speaker_embeddings = None
else:
speaker_embeddings = None
speaker_ids = None
# set stop targets view, we predict a single stop token per iteration.
stop_targets = stop_targets.view(text_input.shape[0],
stop_targets.size(1) // c.r, -1)
stop_targets = (stop_targets.sum(2) > 0.0).unsqueeze(2).float().squeeze(2)
# dispatch data to GPU
if use_cuda:
text_input = text_input.cuda(non_blocking=True)
text_lengths = text_lengths.cuda(non_blocking=True)
mel_input = mel_input.cuda(non_blocking=True)
mel_lengths = mel_lengths.cuda(non_blocking=True)
linear_input = linear_input.cuda(
non_blocking=True) if c.model in ["Tacotron"] else None
stop_targets = stop_targets.cuda(non_blocking=True)
if speaker_ids is not None:
speaker_ids = speaker_ids.cuda(non_blocking=True)
if speaker_embeddings is not None:
speaker_embeddings = speaker_embeddings.cuda(non_blocking=True)
return text_input, text_lengths, mel_input, mel_lengths, linear_input, stop_targets, speaker_ids, speaker_embeddings, avg_text_length, avg_spec_length
def load_tts(self, tts_checkpoint, tts_config, use_cuda):
# pylint: disable=global-statement
global symbols, phonemes
print(" > Loading TTS model ...")
print(" | > model config: ", tts_config)
print(" | > checkpoint file: ", tts_checkpoint)
self.tts_config = load_config(tts_config)
self.use_phonemes = self.tts_config.use_phonemes
self.ap = AudioProcessor(**self.tts_config.audio)
if 'characters' in self.tts_config.keys():
symbols, phonemes = make_symbols(**self.tts_config.characters)
if self.use_phonemes:
self.input_size = len(phonemes)
else:
self.input_size = len(symbols)
# TODO: fix this for multi-speaker model - load speakers
if self.config.tts_speakers is not None:
self.tts_speakers = load_speaker_mapping(self.config.tts_speakers)
num_speakers = len(self.tts_speakers)
else:
num_speakers = 0
self.tts_model = setup_model(self.input_size,
num_speakers=num_speakers,
c=self.tts_config)
# load model state
cp = torch.load(tts_checkpoint, map_location=torch.device('cpu'))
# load the model
self.tts_model.load_state_dict(cp['model'])
if use_cuda:
self.tts_model.cuda()
self.tts_model.eval()
self.tts_model.decoder.max_decoder_steps = 3000
if 'r' in cp:
self.tts_model.decoder.set_r(cp['r'])
print(f" > model reduction factor: {cp['r']}")
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)
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:
prev_out_path = os.path.dirname(args.restore_path)
speaker_mapping = load_speaker_mapping(prev_out_path)
assert all([speaker in speaker_mapping
for speaker in speakers]), "As of now you, you cannot " \
"introduce new speakers to " \
"a previously trained model."
else:
speaker_mapping = {name: i for i, name in enumerate(speakers)}
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
# setup model
model = setup_model(num_chars, num_speakers, c)
optimizer = RAdam(model.parameters(), lr=c.lr, weight_decay=0, betas=(0.9, 0.98), eps=1e-9)
criterion = GlowTTSLoss()
if c.apex_amp_level:
# pylint: disable=import-outside-toplevel
from apex import amp
from apex.parallel import DistributedDataParallel as DDP
model.cuda()
model, optimizer = amp.initialize(model, optimizer, opt_level=c.apex_amp_level)
else:
amp = None
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: #pylint: disable=bare-except
print(" > Partial model initialization.")
model_dict = model.state_dict()
model_dict = set_init_dict(model_dict, checkpoint['model'], c)
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['initial_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 = DDP(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
model = data_depended_init(model, ap)
for epoch in range(0, c.epochs):
c_logger.print_epoch_start(epoch, c.epochs)
train_avg_loss_dict, global_step = train(model, criterion, optimizer,
scheduler, ap, global_step,
epoch, amp)
eval_avg_loss_dict = evaluate(model, criterion, ap, global_step, epoch)
c_logger.print_epoch_end(epoch, eval_avg_loss_dict)
target_loss = train_avg_loss_dict['avg_loss']
if c.run_eval:
target_loss = eval_avg_loss_dict['avg_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)
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:
prev_out_path = os.path.dirname(args.restore_path)
speaker_mapping = load_speaker_mapping(prev_out_path)
assert all([speaker in speaker_mapping
for speaker in speakers]), "As of now you, you cannot " \
"introduce new speakers to " \
"a previously trained model."
else:
speaker_mapping = {name: i for i, name in enumerate(speakers)}
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
model = setup_model(num_chars, num_speakers, c)
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
# 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:
print(" > Partial model initialization.")
model_dict = model.state_dict()
model_dict = set_init_dict(model_dict, checkpoint['model'], c)
model.load_state_dict(model_dict)
del model_dict
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)
eval_avg_loss_dict = evaluate(model, criterion, ap, global_step, epoch)
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)
