Dev 2.3. (#242)
* Fix inputs of duration discriminator * Add LSTM * Update models.py * Update tensorboard scalar * Noise injection for minimizing modality gap * Update infer.py * support bf16 run * del unused_para flag * support bf16 config * add grad clip * fix(logger and grad):add dur grad,fix grad clip * Update webui_preprocess.py * Fix English G2P * fix(bert_gen):add pass * Pass SDP to DD * Update webui_preprocess.py * Update config.json * Update webui.py * Update chinese_bert.py * Upload webui for deploy * Update webui.py * torch.save as pt not npy * Update config.json * add freeze emo vq * Update webui_preprocess.py * Fix tone_sandhi.py * Comment up grad clip * Fix in-place addition * Add SLM discriminator * Add DDP for WD * Feat: Style text: make emotions and style similar to the style text by mixing bert (#240) (#241) * fix:(oldVersion210) Load on demand Emotion model * feat: update fastapi.py. 添加更多错误日志信息 * Switch pyopenjtalk to pyopenjtalk-prebuilt * fix: update fastapi.py. 2.2 reference适配 * Update resample.py * 修复Onnx导出的BUG (#237) * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add files via upload * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Delete attentions_onnx.py * Delete models_onnx.py * Add files via upload * Add files via upload * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update __init__.py * Update __init__.py * Update __init__.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- * Fix onnx * Format export * Feat: style-text and bert mixing (JA only) * Ensure the same tensor shape * Update * update gradio version * Fix * Style text for chinese and english (ver 2.2) * Style text for chinese and english (ver 2.1) * Style text in FastAPI * Translate style text desc in chinese --------- Co-authored-by: litagin02 <139731664+litagin02@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: Ναρουσέ·μ·γιουμεμί·Χινακάννα <40709280+NaruseMioShirakana@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Remove CLAP * Revert "Remove CLAP" This reverts commit 62fd59bc837c580239840a2bc84b15e0663730fc. Revert * Remove CLAP * bf16 audo grad cilp * Update webui and infer utils * Update webui.py * Update webui.py * Update webui-preprocess.py * Update webui_preprocess.py --------- Co-authored-by: Sihan Wang <wangsihan1995@gmail.com> Co-authored-by: OedoSoldier <31711261+OedoSoldier@users.noreply.github.com> Co-authored-by: litagin02 <139731664+litagin02@users.noreply.github.com> Co-authored-by: Sora <654163754@qq.com> Co-authored-by: Ναρουσέ·μ·γιουμεμί·Χινακάννα <40709280+NaruseMioShirakana@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
Stardust·减
230
train_ms.py
230
train_ms.py
@@ -27,8 +27,15 @@ from models import (
|
||||
SynthesizerTrn,
|
||||
MultiPeriodDiscriminator,
|
||||
DurationDiscriminator,
|
||||
WavLMDiscriminator,
|
||||
)
|
||||
from losses import (
|
||||
generator_loss,
|
||||
discriminator_loss,
|
||||
feature_loss,
|
||||
kl_loss,
|
||||
WavLMLoss,
|
||||
)
|
||||
from losses import generator_loss, discriminator_loss, feature_loss, kl_loss
|
||||
from mel_processing import mel_spectrogram_torch, spec_to_mel_torch
|
||||
from text.symbols import symbols
|
||||
|
||||
@@ -42,7 +49,6 @@ torch.backends.cuda.enable_flash_sdp(True)
|
||||
torch.backends.cuda.enable_mem_efficient_sdp(
|
||||
True
|
||||
) # Not available if torch version is lower than 2.0
|
||||
torch.backends.cuda.enable_math_sdp(True)
|
||||
global_step = 0
|
||||
|
||||
|
||||
@@ -173,6 +179,8 @@ def run():
|
||||
0.1,
|
||||
gin_channels=hps.model.gin_channels if hps.data.n_speakers != 0 else 0,
|
||||
).cuda(local_rank)
|
||||
else:
|
||||
net_dur_disc = None
|
||||
if (
|
||||
"use_spk_conditioned_encoder" in hps.model.keys()
|
||||
and hps.model.use_spk_conditioned_encoder is True
|
||||
@@ -210,6 +218,9 @@ def run():
|
||||
param.requires_grad = False
|
||||
|
||||
net_d = MultiPeriodDiscriminator(hps.model.use_spectral_norm).cuda(local_rank)
|
||||
net_wd = WavLMDiscriminator(
|
||||
hps.model.slm.hidden, hps.model.slm.nlayers, hps.model.slm.initial_channel
|
||||
).cuda(local_rank)
|
||||
optim_g = torch.optim.AdamW(
|
||||
filter(lambda p: p.requires_grad, net_g.parameters()),
|
||||
hps.train.learning_rate,
|
||||
@@ -222,6 +233,12 @@ def run():
|
||||
betas=hps.train.betas,
|
||||
eps=hps.train.eps,
|
||||
)
|
||||
optim_wd = torch.optim.AdamW(
|
||||
net_wd.parameters(),
|
||||
hps.train.learning_rate,
|
||||
betas=hps.train.betas,
|
||||
eps=hps.train.eps,
|
||||
)
|
||||
if net_dur_disc is not None:
|
||||
optim_dur_disc = torch.optim.AdamW(
|
||||
net_dur_disc.parameters(),
|
||||
@@ -233,12 +250,11 @@ def run():
|
||||
optim_dur_disc = None
|
||||
net_g = DDP(net_g, device_ids=[local_rank], bucket_cap_mb=512)
|
||||
net_d = DDP(net_d, device_ids=[local_rank], bucket_cap_mb=512)
|
||||
dur_resume_lr = None
|
||||
net_wd = DDP(net_wd, device_ids=[local_rank], bucket_cap_mb=512)
|
||||
if net_dur_disc is not None:
|
||||
net_dur_disc = DDP(
|
||||
net_dur_disc,
|
||||
device_ids=[local_rank],
|
||||
find_unused_parameters=True,
|
||||
bucket_cap_mb=512,
|
||||
)
|
||||
|
||||
@@ -250,9 +266,10 @@ def run():
|
||||
token=config.openi_token,
|
||||
mirror=config.mirror,
|
||||
)
|
||||
|
||||
try:
|
||||
if net_dur_disc is not None:
|
||||
dur_resume_lr = hps.train.learning_rate
|
||||
wd_resume_lr = hps.train.learning_rate
|
||||
if net_dur_disc is not None:
|
||||
try:
|
||||
_, _, dur_resume_lr, epoch_str = utils.load_checkpoint(
|
||||
utils.latest_checkpoint_path(hps.model_dir, "DUR_*.pth"),
|
||||
net_dur_disc,
|
||||
@@ -261,28 +278,32 @@ def run():
|
||||
if "skip_optimizer" in hps.train
|
||||
else True,
|
||||
)
|
||||
_, optim_g, g_resume_lr, epoch_str = utils.load_checkpoint(
|
||||
utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"),
|
||||
net_g,
|
||||
optim_g,
|
||||
skip_optimizer=hps.train.skip_optimizer
|
||||
if "skip_optimizer" in hps.train
|
||||
else True,
|
||||
)
|
||||
_, optim_d, d_resume_lr, epoch_str = utils.load_checkpoint(
|
||||
utils.latest_checkpoint_path(hps.model_dir, "D_*.pth"),
|
||||
net_d,
|
||||
optim_d,
|
||||
skip_optimizer=hps.train.skip_optimizer
|
||||
if "skip_optimizer" in hps.train
|
||||
else True,
|
||||
)
|
||||
if not optim_g.param_groups[0].get("initial_lr"):
|
||||
optim_g.param_groups[0]["initial_lr"] = g_resume_lr
|
||||
if not optim_d.param_groups[0].get("initial_lr"):
|
||||
optim_d.param_groups[0]["initial_lr"] = d_resume_lr
|
||||
if not optim_dur_disc.param_groups[0].get("initial_lr"):
|
||||
optim_dur_disc.param_groups[0]["initial_lr"] = dur_resume_lr
|
||||
except:
|
||||
print("Initialize dur_disc")
|
||||
|
||||
try:
|
||||
_, optim_g, g_resume_lr, epoch_str = utils.load_checkpoint(
|
||||
utils.latest_checkpoint_path(hps.model_dir, "G_*.pth"),
|
||||
net_g,
|
||||
optim_g,
|
||||
skip_optimizer=hps.train.skip_optimizer
|
||||
if "skip_optimizer" in hps.train
|
||||
else True,
|
||||
)
|
||||
_, optim_d, d_resume_lr, epoch_str = utils.load_checkpoint(
|
||||
utils.latest_checkpoint_path(hps.model_dir, "D_*.pth"),
|
||||
net_d,
|
||||
optim_d,
|
||||
skip_optimizer=hps.train.skip_optimizer
|
||||
if "skip_optimizer" in hps.train
|
||||
else True,
|
||||
)
|
||||
if not optim_g.param_groups[0].get("initial_lr"):
|
||||
optim_g.param_groups[0]["initial_lr"] = g_resume_lr
|
||||
if not optim_d.param_groups[0].get("initial_lr"):
|
||||
optim_d.param_groups[0]["initial_lr"] = d_resume_lr
|
||||
|
||||
epoch_str = max(epoch_str, 1)
|
||||
# global_step = (epoch_str - 1) * len(train_loader)
|
||||
@@ -297,21 +318,36 @@ def run():
|
||||
epoch_str = 1
|
||||
global_step = 0
|
||||
|
||||
try:
|
||||
_, optim_wd, wd_resume_lr, epoch_str = utils.load_checkpoint(
|
||||
utils.latest_checkpoint_path(hps.model_dir, "WD_*.pth"),
|
||||
net_wd,
|
||||
optim_wd,
|
||||
skip_optimizer=hps.train.skip_optimizer
|
||||
if "skip_optimizer" in hps.train
|
||||
else True,
|
||||
)
|
||||
if not optim_wd.param_groups[0].get("initial_lr"):
|
||||
optim_wd.param_groups[0]["initial_lr"] = wd_resume_lr
|
||||
except Exception as e:
|
||||
print(e)
|
||||
|
||||
scheduler_g = torch.optim.lr_scheduler.ExponentialLR(
|
||||
optim_g, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
|
||||
)
|
||||
scheduler_d = torch.optim.lr_scheduler.ExponentialLR(
|
||||
optim_d, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
|
||||
)
|
||||
scheduler_wd = torch.optim.lr_scheduler.ExponentialLR(
|
||||
optim_wd, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
|
||||
)
|
||||
if net_dur_disc is not None:
|
||||
if not optim_dur_disc.param_groups[0].get("initial_lr"):
|
||||
optim_dur_disc.param_groups[0]["initial_lr"] = dur_resume_lr
|
||||
scheduler_dur_disc = torch.optim.lr_scheduler.ExponentialLR(
|
||||
optim_dur_disc, gamma=hps.train.lr_decay, last_epoch=epoch_str - 2
|
||||
)
|
||||
else:
|
||||
scheduler_dur_disc = None
|
||||
scaler = GradScaler(enabled=hps.train.fp16_run)
|
||||
scaler = GradScaler(enabled=hps.train.bf16_run)
|
||||
|
||||
for epoch in range(epoch_str, hps.train.epochs + 1):
|
||||
if rank == 0:
|
||||
@@ -320,9 +356,9 @@ def run():
|
||||
local_rank,
|
||||
epoch,
|
||||
hps,
|
||||
[net_g, net_d, net_dur_disc],
|
||||
[optim_g, optim_d, optim_dur_disc],
|
||||
[scheduler_g, scheduler_d, scheduler_dur_disc],
|
||||
[net_g, net_d, net_dur_disc, net_wd],
|
||||
[optim_g, optim_d, optim_dur_disc, optim_wd],
|
||||
[scheduler_g, scheduler_d, scheduler_dur_disc, scheduler_wd],
|
||||
scaler,
|
||||
[train_loader, eval_loader],
|
||||
logger,
|
||||
@@ -334,9 +370,9 @@ def run():
|
||||
local_rank,
|
||||
epoch,
|
||||
hps,
|
||||
[net_g, net_d, net_dur_disc],
|
||||
[optim_g, optim_d, optim_dur_disc],
|
||||
[scheduler_g, scheduler_d, scheduler_dur_disc],
|
||||
[net_g, net_d, net_dur_disc, net_wd],
|
||||
[optim_g, optim_d, optim_dur_disc, optim_wd],
|
||||
[scheduler_g, scheduler_d, scheduler_dur_disc, scheduler_wd],
|
||||
scaler,
|
||||
[train_loader, None],
|
||||
None,
|
||||
@@ -361,18 +397,25 @@ def train_and_evaluate(
|
||||
logger,
|
||||
writers,
|
||||
):
|
||||
net_g, net_d, net_dur_disc = nets
|
||||
optim_g, optim_d, optim_dur_disc = optims
|
||||
scheduler_g, scheduler_d, scheduler_dur_disc = schedulers
|
||||
net_g, net_d, net_dur_disc, net_wd = nets
|
||||
optim_g, optim_d, optim_dur_disc, optim_wd = optims
|
||||
scheduler_g, scheduler_d, scheduler_dur_disc, scheduler_wd = schedulers
|
||||
train_loader, eval_loader = loaders
|
||||
if writers is not None:
|
||||
writer, writer_eval = writers
|
||||
wl = WavLMLoss(
|
||||
hps.model.slm.model,
|
||||
net_wd,
|
||||
hps.data.sampling_rate,
|
||||
hps.model.slm.sr,
|
||||
).to(local_rank)
|
||||
|
||||
train_loader.batch_sampler.set_epoch(epoch)
|
||||
global global_step
|
||||
|
||||
net_g.train()
|
||||
net_d.train()
|
||||
net_wd.train()
|
||||
if net_dur_disc is not None:
|
||||
net_dur_disc.train()
|
||||
for batch_idx, (
|
||||
@@ -388,7 +431,6 @@ def train_and_evaluate(
|
||||
bert,
|
||||
ja_bert,
|
||||
en_bert,
|
||||
emo,
|
||||
) in enumerate(tqdm(train_loader)):
|
||||
if net_g.module.use_noise_scaled_mas:
|
||||
current_mas_noise_scale = (
|
||||
@@ -411,9 +453,8 @@ def train_and_evaluate(
|
||||
bert = bert.cuda(local_rank, non_blocking=True)
|
||||
ja_bert = ja_bert.cuda(local_rank, non_blocking=True)
|
||||
en_bert = en_bert.cuda(local_rank, non_blocking=True)
|
||||
emo = emo.cuda(local_rank, non_blocking=True)
|
||||
|
||||
with autocast(enabled=hps.train.fp16_run):
|
||||
with autocast(enabled=hps.train.bf16_run, dtype=torch.bfloat16):
|
||||
(
|
||||
y_hat,
|
||||
l_length,
|
||||
@@ -422,9 +463,8 @@ def train_and_evaluate(
|
||||
x_mask,
|
||||
z_mask,
|
||||
(z, z_p, m_p, logs_p, m_q, logs_q),
|
||||
(hidden_x, logw, logw_),
|
||||
(hidden_x, logw, logw_, logw_sdp),
|
||||
g,
|
||||
loss_commit,
|
||||
) = net_g(
|
||||
x,
|
||||
x_lengths,
|
||||
@@ -436,7 +476,6 @@ def train_and_evaluate(
|
||||
bert,
|
||||
ja_bert,
|
||||
en_bert,
|
||||
emo,
|
||||
)
|
||||
mel = spec_to_mel_torch(
|
||||
spec,
|
||||
@@ -450,7 +489,7 @@ def train_and_evaluate(
|
||||
mel, ids_slice, hps.train.segment_size // hps.data.hop_length
|
||||
)
|
||||
y_hat_mel = mel_spectrogram_torch(
|
||||
y_hat.squeeze(1),
|
||||
y_hat.squeeze(1).float(),
|
||||
hps.data.filter_length,
|
||||
hps.data.n_mel_channels,
|
||||
hps.data.sampling_rate,
|
||||
@@ -466,7 +505,7 @@ def train_and_evaluate(
|
||||
|
||||
# Discriminator
|
||||
y_d_hat_r, y_d_hat_g, _, _ = net_d(y, y_hat.detach())
|
||||
with autocast(enabled=False):
|
||||
with autocast(enabled=hps.train.bf16_run, dtype=torch.bfloat16):
|
||||
loss_disc, losses_disc_r, losses_disc_g = discriminator_loss(
|
||||
y_d_hat_r, y_d_hat_g
|
||||
)
|
||||
@@ -475,11 +514,20 @@ def train_and_evaluate(
|
||||
y_dur_hat_r, y_dur_hat_g = net_dur_disc(
|
||||
hidden_x.detach(),
|
||||
x_mask.detach(),
|
||||
logw.detach(),
|
||||
logw_.detach(),
|
||||
logw.detach(),
|
||||
g.detach(),
|
||||
)
|
||||
with autocast(enabled=False):
|
||||
y_dur_hat_r_sdp, y_dur_hat_g_sdp = net_dur_disc(
|
||||
hidden_x.detach(),
|
||||
x_mask.detach(),
|
||||
logw_.detach(),
|
||||
logw_sdp.detach(),
|
||||
g.detach(),
|
||||
)
|
||||
y_dur_hat_r = y_dur_hat_r + y_dur_hat_r_sdp
|
||||
y_dur_hat_g = y_dur_hat_g + y_dur_hat_g_sdp
|
||||
with autocast(enabled=hps.train.bf16_run, dtype=torch.bfloat16):
|
||||
# TODO: I think need to mean using the mask, but for now, just mean all
|
||||
(
|
||||
loss_dur_disc,
|
||||
@@ -490,31 +538,60 @@ def train_and_evaluate(
|
||||
optim_dur_disc.zero_grad()
|
||||
scaler.scale(loss_dur_disc_all).backward()
|
||||
scaler.unscale_(optim_dur_disc)
|
||||
commons.clip_grad_value_(net_dur_disc.parameters(), None)
|
||||
# torch.nn.utils.clip_grad_norm_(
|
||||
# parameters=net_dur_disc.parameters(), max_norm=100
|
||||
# )
|
||||
grad_norm_dur = commons.clip_grad_value_(
|
||||
net_dur_disc.parameters(), None
|
||||
)
|
||||
scaler.step(optim_dur_disc)
|
||||
|
||||
optim_d.zero_grad()
|
||||
scaler.scale(loss_disc_all).backward()
|
||||
scaler.unscale_(optim_d)
|
||||
if getattr(hps.train, "bf16_run", False):
|
||||
torch.nn.utils.clip_grad_norm_(parameters=net_d.parameters(), max_norm=200)
|
||||
grad_norm_d = commons.clip_grad_value_(net_d.parameters(), None)
|
||||
scaler.step(optim_d)
|
||||
|
||||
with autocast(enabled=hps.train.fp16_run):
|
||||
with autocast(enabled=hps.train.bf16_run, dtype=torch.bfloat16):
|
||||
loss_slm = wl.discriminator(
|
||||
y.detach().squeeze(), y_hat.detach().squeeze()
|
||||
).mean()
|
||||
|
||||
optim_wd.zero_grad()
|
||||
scaler.scale(loss_slm).backward()
|
||||
scaler.unscale_(optim_wd)
|
||||
# torch.nn.utils.clip_grad_norm_(parameters=net_wd.parameters(), max_norm=200)
|
||||
grad_norm_wd = commons.clip_grad_value_(net_wd.parameters(), None)
|
||||
scaler.step(optim_wd)
|
||||
|
||||
with autocast(enabled=hps.train.bf16_run, dtype=torch.bfloat16):
|
||||
# Generator
|
||||
y_d_hat_r, y_d_hat_g, fmap_r, fmap_g = net_d(y, y_hat)
|
||||
if net_dur_disc is not None:
|
||||
y_dur_hat_r, y_dur_hat_g = net_dur_disc(
|
||||
hidden_x, x_mask, logw, logw_, g
|
||||
)
|
||||
with autocast(enabled=False):
|
||||
_, y_dur_hat_g = net_dur_disc(hidden_x, x_mask, logw_, logw, g)
|
||||
_, y_dur_hat_g_sdp = net_dur_disc(hidden_x, x_mask, logw_, logw_sdp, g)
|
||||
y_dur_hat_g = y_dur_hat_g + y_dur_hat_g_sdp
|
||||
with autocast(enabled=hps.train.bf16_run, dtype=torch.bfloat16):
|
||||
loss_dur = torch.sum(l_length.float())
|
||||
loss_mel = F.l1_loss(y_mel, y_hat_mel) * hps.train.c_mel
|
||||
loss_kl = kl_loss(z_p, logs_q, m_p, logs_p, z_mask) * hps.train.c_kl
|
||||
|
||||
loss_fm = feature_loss(fmap_r, fmap_g)
|
||||
loss_gen, losses_gen = generator_loss(y_d_hat_g)
|
||||
|
||||
loss_lm = wl(y.detach().squeeze(), y_hat.squeeze()).mean()
|
||||
loss_lm_gen = wl.generator(y_hat.squeeze())
|
||||
|
||||
loss_gen_all = (
|
||||
loss_gen + loss_fm + loss_mel + loss_dur + loss_kl + loss_commit
|
||||
loss_gen
|
||||
+ loss_fm
|
||||
+ loss_mel
|
||||
+ loss_dur
|
||||
+ loss_kl
|
||||
+ loss_lm
|
||||
+ loss_lm_gen
|
||||
)
|
||||
if net_dur_disc is not None:
|
||||
loss_dur_gen, losses_dur_gen = generator_loss(y_dur_hat_g)
|
||||
@@ -522,6 +599,8 @@ def train_and_evaluate(
|
||||
optim_g.zero_grad()
|
||||
scaler.scale(loss_gen_all).backward()
|
||||
scaler.unscale_(optim_g)
|
||||
if getattr(hps.train, "bf16_run", False):
|
||||
torch.nn.utils.clip_grad_norm_(parameters=net_g.parameters(), max_norm=500)
|
||||
grad_norm_g = commons.clip_grad_value_(net_g.parameters(), None)
|
||||
scaler.step(optim_g)
|
||||
scaler.update()
|
||||
@@ -540,9 +619,12 @@ def train_and_evaluate(
|
||||
scalar_dict = {
|
||||
"loss/g/total": loss_gen_all,
|
||||
"loss/d/total": loss_disc_all,
|
||||
"loss/wd/total": loss_slm,
|
||||
"learning_rate": lr,
|
||||
"grad_norm_d": grad_norm_d,
|
||||
"grad_norm_g": grad_norm_g,
|
||||
"grad_norm_dur": grad_norm_dur,
|
||||
"grad_norm_wd": grad_norm_wd,
|
||||
}
|
||||
scalar_dict.update(
|
||||
{
|
||||
@@ -550,6 +632,8 @@ def train_and_evaluate(
|
||||
"loss/g/mel": loss_mel,
|
||||
"loss/g/dur": loss_dur,
|
||||
"loss/g/kl": loss_kl,
|
||||
"loss/g/lm": loss_lm,
|
||||
"loss/g/lm_gen": loss_lm_gen,
|
||||
}
|
||||
)
|
||||
scalar_dict.update(
|
||||
@@ -562,6 +646,30 @@ def train_and_evaluate(
|
||||
{"loss/d_g/{}".format(i): v for i, v in enumerate(losses_disc_g)}
|
||||
)
|
||||
|
||||
if net_dur_disc is not None:
|
||||
scalar_dict.update({"loss/dur_disc/total": loss_dur_disc_all})
|
||||
|
||||
scalar_dict.update(
|
||||
{
|
||||
"loss/dur_disc_g/{}".format(i): v
|
||||
for i, v in enumerate(losses_dur_disc_g)
|
||||
}
|
||||
)
|
||||
scalar_dict.update(
|
||||
{
|
||||
"loss/dur_disc_r/{}".format(i): v
|
||||
for i, v in enumerate(losses_dur_disc_r)
|
||||
}
|
||||
)
|
||||
|
||||
scalar_dict.update({"loss/g/dur_gen": loss_dur_gen})
|
||||
scalar_dict.update(
|
||||
{
|
||||
"loss/g/dur_gen_{}".format(i): v
|
||||
for i, v in enumerate(losses_dur_gen)
|
||||
}
|
||||
)
|
||||
|
||||
image_dict = {
|
||||
"slice/mel_org": utils.plot_spectrogram_to_numpy(
|
||||
y_mel[0].data.cpu().numpy()
|
||||
@@ -599,6 +707,13 @@ def train_and_evaluate(
|
||||
epoch,
|
||||
os.path.join(hps.model_dir, "D_{}.pth".format(global_step)),
|
||||
)
|
||||
utils.save_checkpoint(
|
||||
net_wd,
|
||||
optim_wd,
|
||||
hps.train.learning_rate,
|
||||
epoch,
|
||||
os.path.join(hps.model_dir, "WD_{}.pth".format(global_step)),
|
||||
)
|
||||
if net_dur_disc is not None:
|
||||
utils.save_checkpoint(
|
||||
net_dur_disc,
|
||||
@@ -642,7 +757,6 @@ def evaluate(hps, generator, eval_loader, writer_eval):
|
||||
bert,
|
||||
ja_bert,
|
||||
en_bert,
|
||||
emo,
|
||||
) in enumerate(eval_loader):
|
||||
x, x_lengths = x.cuda(), x_lengths.cuda()
|
||||
spec, spec_lengths = spec.cuda(), spec_lengths.cuda()
|
||||
@@ -653,7 +767,6 @@ def evaluate(hps, generator, eval_loader, writer_eval):
|
||||
en_bert = en_bert.cuda()
|
||||
tone = tone.cuda()
|
||||
language = language.cuda()
|
||||
emo = emo.cuda()
|
||||
for use_sdp in [True, False]:
|
||||
y_hat, attn, mask, *_ = generator.module.infer(
|
||||
x,
|
||||
@@ -664,7 +777,6 @@ def evaluate(hps, generator, eval_loader, writer_eval):
|
||||
bert,
|
||||
ja_bert,
|
||||
en_bert,
|
||||
emo,
|
||||
y=spec,
|
||||
max_len=1000,
|
||||
sdp_ratio=0.0 if not use_sdp else 1.0,
|
||||
|
||||
Reference in New Issue
Block a user