Spaces:
Sleeping
Sleeping
File size: 13,755 Bytes
b725c5a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 |
import torch
import numpy as np
from torch.utils.data import ConcatDataset, DataLoader
from models.tts.naturalspeech2.base_trainer import TTSTrainer
from models.base.base_trainer import BaseTrainer
from models.base.base_sampler import VariableSampler
from models.tts.naturalspeech2.ns2_dataset import NS2Dataset, NS2Collator, batch_by_size
from models.tts.naturalspeech2.ns2_loss import (
log_pitch_loss,
log_dur_loss,
diff_loss,
diff_ce_loss,
)
from torch.utils.data.sampler import BatchSampler, SequentialSampler
from models.tts.naturalspeech2.ns2 import NaturalSpeech2
from torch.optim import Adam, AdamW
from torch.nn import MSELoss, L1Loss
import torch.nn.functional as F
from diffusers import get_scheduler
class NS2Trainer(TTSTrainer):
def __init__(self, args, cfg):
TTSTrainer.__init__(self, args, cfg)
def _build_model(self):
model = NaturalSpeech2(cfg=self.cfg.model)
return model
def _build_dataset(self):
return NS2Dataset, NS2Collator
def _build_dataloader(self):
if self.cfg.train.use_dynamic_batchsize:
print("Use Dynamic Batchsize......")
Dataset, Collator = self._build_dataset()
train_dataset = Dataset(self.cfg, self.cfg.dataset[0], is_valid=False)
train_collate = Collator(self.cfg)
batch_sampler = batch_by_size(
train_dataset.num_frame_indices,
train_dataset.get_num_frames,
max_tokens=self.cfg.train.max_tokens * self.accelerator.num_processes,
max_sentences=self.cfg.train.max_sentences
* self.accelerator.num_processes,
required_batch_size_multiple=self.accelerator.num_processes,
)
np.random.seed(980205)
np.random.shuffle(batch_sampler)
print(batch_sampler[:1])
batches = [
x[
self.accelerator.local_process_index :: self.accelerator.num_processes
]
for x in batch_sampler
if len(x) % self.accelerator.num_processes == 0
]
train_loader = DataLoader(
train_dataset,
collate_fn=train_collate,
num_workers=self.cfg.train.dataloader.num_worker,
batch_sampler=VariableSampler(
batches, drop_last=False, use_random_sampler=True
),
pin_memory=self.cfg.train.dataloader.pin_memory,
)
self.accelerator.wait_for_everyone()
valid_dataset = Dataset(self.cfg, self.cfg.dataset[0], is_valid=True)
valid_collate = Collator(self.cfg)
batch_sampler = batch_by_size(
valid_dataset.num_frame_indices,
valid_dataset.get_num_frames,
max_tokens=self.cfg.train.max_tokens * self.accelerator.num_processes,
max_sentences=self.cfg.train.max_sentences
* self.accelerator.num_processes,
required_batch_size_multiple=self.accelerator.num_processes,
)
batches = [
x[
self.accelerator.local_process_index :: self.accelerator.num_processes
]
for x in batch_sampler
if len(x) % self.accelerator.num_processes == 0
]
valid_loader = DataLoader(
valid_dataset,
collate_fn=valid_collate,
num_workers=self.cfg.train.dataloader.num_worker,
batch_sampler=VariableSampler(batches, drop_last=False),
pin_memory=self.cfg.train.dataloader.pin_memory,
)
self.accelerator.wait_for_everyone()
else:
print("Use Normal Batchsize......")
Dataset, Collator = self._build_dataset()
train_dataset = Dataset(self.cfg, self.cfg.dataset[0], is_valid=False)
train_collate = Collator(self.cfg)
train_loader = DataLoader(
train_dataset,
shuffle=True,
collate_fn=train_collate,
batch_size=self.cfg.train.batch_size,
num_workers=self.cfg.train.dataloader.num_worker,
pin_memory=self.cfg.train.dataloader.pin_memory,
)
valid_dataset = Dataset(self.cfg, self.cfg.dataset[0], is_valid=True)
valid_collate = Collator(self.cfg)
valid_loader = DataLoader(
valid_dataset,
shuffle=True,
collate_fn=valid_collate,
batch_size=self.cfg.train.batch_size,
num_workers=self.cfg.train.dataloader.num_worker,
pin_memory=self.cfg.train.dataloader.pin_memory,
)
self.accelerator.wait_for_everyone()
return train_loader, valid_loader
def _build_optimizer(self):
optimizer = torch.optim.AdamW(
filter(lambda p: p.requires_grad, self.model.parameters()),
**self.cfg.train.adam
)
return optimizer
def _build_scheduler(self):
lr_scheduler = get_scheduler(
self.cfg.train.lr_scheduler,
optimizer=self.optimizer,
num_warmup_steps=self.cfg.train.lr_warmup_steps,
num_training_steps=self.cfg.train.num_train_steps,
)
return lr_scheduler
def _build_criterion(self):
criterion = torch.nn.L1Loss(reduction="mean")
return criterion
def write_summary(self, losses, stats):
for key, value in losses.items():
self.sw.add_scalar(key, value, self.step)
def write_valid_summary(self, losses, stats):
for key, value in losses.items():
self.sw.add_scalar(key, value, self.step)
def get_state_dict(self):
state_dict = {
"model": self.model.state_dict(),
"optimizer": self.optimizer.state_dict(),
"scheduler": self.scheduler.state_dict(),
"step": self.step,
"epoch": self.epoch,
"batch_size": self.cfg.train.batch_size,
}
return state_dict
def load_model(self, checkpoint):
self.step = checkpoint["step"]
self.epoch = checkpoint["epoch"]
self.model.load_state_dict(checkpoint["model"])
self.optimizer.load_state_dict(checkpoint["optimizer"])
self.scheduler.load_state_dict(checkpoint["scheduler"])
def _train_step(self, batch):
train_losses = {}
total_loss = 0
train_stats = {}
code = batch["code"] # (B, 16, T)
pitch = batch["pitch"] # (B, T)
duration = batch["duration"] # (B, N)
phone_id = batch["phone_id"] # (B, N)
ref_code = batch["ref_code"] # (B, 16, T')
phone_mask = batch["phone_mask"] # (B, N)
mask = batch["mask"] # (B, T)
ref_mask = batch["ref_mask"] # (B, T')
diff_out, prior_out = self.model(
code=code,
pitch=pitch,
duration=duration,
phone_id=phone_id,
ref_code=ref_code,
phone_mask=phone_mask,
mask=mask,
ref_mask=ref_mask,
)
# pitch loss
pitch_loss = log_pitch_loss(prior_out["pitch_pred_log"], pitch, mask=mask)
total_loss += pitch_loss
train_losses["pitch_loss"] = pitch_loss
# duration loss
dur_loss = log_dur_loss(prior_out["dur_pred_log"], duration, mask=phone_mask)
total_loss += dur_loss
train_losses["dur_loss"] = dur_loss
x0 = self.model.module.code_to_latent(code)
if self.cfg.model.diffusion.diffusion_type == "diffusion":
# diff loss x0
diff_loss_x0 = diff_loss(diff_out["x0_pred"], x0, mask=mask)
total_loss += diff_loss_x0
train_losses["diff_loss_x0"] = diff_loss_x0
# diff loss noise
diff_loss_noise = diff_loss(
diff_out["noise_pred"], diff_out["noise"], mask=mask
)
total_loss += diff_loss_noise * self.cfg.train.diff_noise_loss_lambda
train_losses["diff_loss_noise"] = diff_loss_noise
elif self.cfg.model.diffusion.diffusion_type == "flow":
# diff flow matching loss
flow_gt = diff_out["noise"] - x0
diff_loss_flow = diff_loss(diff_out["flow_pred"], flow_gt, mask=mask)
total_loss += diff_loss_flow
train_losses["diff_loss_flow"] = diff_loss_flow
# diff loss ce
# (nq, B, T); (nq, B, T, 1024)
if self.cfg.train.diff_ce_loss_lambda > 0:
pred_indices, pred_dist = self.model.module.latent_to_code(
diff_out["x0_pred"], nq=code.shape[1]
)
gt_indices, _ = self.model.module.latent_to_code(x0, nq=code.shape[1])
diff_loss_ce = diff_ce_loss(pred_dist, gt_indices, mask=mask)
total_loss += diff_loss_ce * self.cfg.train.diff_ce_loss_lambda
train_losses["diff_loss_ce"] = diff_loss_ce
self.optimizer.zero_grad()
# total_loss.backward()
self.accelerator.backward(total_loss)
if self.accelerator.sync_gradients:
self.accelerator.clip_grad_norm_(
filter(lambda p: p.requires_grad, self.model.parameters()), 0.5
)
self.optimizer.step()
self.scheduler.step()
for item in train_losses:
train_losses[item] = train_losses[item].item()
if self.cfg.train.diff_ce_loss_lambda > 0:
pred_indices_list = pred_indices.long().detach().cpu().numpy()
gt_indices_list = gt_indices.long().detach().cpu().numpy()
mask_list = batch["mask"].detach().cpu().numpy()
for i in range(pred_indices_list.shape[0]):
pred_acc = np.sum(
(pred_indices_list[i] == gt_indices_list[i]) * mask_list
) / np.sum(mask_list)
train_losses["pred_acc_{}".format(str(i))] = pred_acc
train_losses["batch_size"] = code.shape[0]
train_losses["max_frame_nums"] = np.max(
batch["frame_nums"].detach().cpu().numpy()
)
return (total_loss.item(), train_losses, train_stats)
@torch.inference_mode()
def _valid_step(self, batch):
valid_losses = {}
total_loss = 0
valid_stats = {}
code = batch["code"] # (B, 16, T)
pitch = batch["pitch"] # (B, T)
duration = batch["duration"] # (B, N)
phone_id = batch["phone_id"] # (B, N)
ref_code = batch["ref_code"] # (B, 16, T')
phone_mask = batch["phone_mask"] # (B, N)
mask = batch["mask"] # (B, T)
ref_mask = batch["ref_mask"] # (B, T')
diff_out, prior_out = self.model(
code=code,
pitch=pitch,
duration=duration,
phone_id=phone_id,
ref_code=ref_code,
phone_mask=phone_mask,
mask=mask,
ref_mask=ref_mask,
)
# pitch loss
pitch_loss = log_pitch_loss(prior_out["pitch_pred_log"], pitch, mask=mask)
total_loss += pitch_loss
valid_losses["pitch_loss"] = pitch_loss
# duration loss
dur_loss = log_dur_loss(prior_out["dur_pred_log"], duration, mask=phone_mask)
total_loss += dur_loss
valid_losses["dur_loss"] = dur_loss
x0 = self.model.module.code_to_latent(code)
if self.cfg.model.diffusion.diffusion_type == "diffusion":
# diff loss x0
diff_loss_x0 = diff_loss(diff_out["x0_pred"], x0, mask=mask)
total_loss += diff_loss_x0
valid_losses["diff_loss_x0"] = diff_loss_x0
# diff loss noise
diff_loss_noise = diff_loss(
diff_out["noise_pred"], diff_out["noise"], mask=mask
)
total_loss += diff_loss_noise * self.cfg.train.diff_noise_loss_lambda
valid_losses["diff_loss_noise"] = diff_loss_noise
elif self.cfg.model.diffusion.diffusion_type == "flow":
# diff flow matching loss
flow_gt = diff_out["noise"] - x0
diff_loss_flow = diff_loss(diff_out["flow_pred"], flow_gt, mask=mask)
total_loss += diff_loss_flow
valid_losses["diff_loss_flow"] = diff_loss_flow
# diff loss ce
# (nq, B, T); (nq, B, T, 1024)
if self.cfg.train.diff_ce_loss_lambda > 0:
pred_indices, pred_dist = self.model.module.latent_to_code(
diff_out["x0_pred"], nq=code.shape[1]
)
gt_indices, _ = self.model.module.latent_to_code(x0, nq=code.shape[1])
diff_loss_ce = diff_ce_loss(pred_dist, gt_indices, mask=mask)
total_loss += diff_loss_ce * self.cfg.train.diff_ce_loss_lambda
valid_losses["diff_loss_ce"] = diff_loss_ce
for item in valid_losses:
valid_losses[item] = valid_losses[item].item()
if self.cfg.train.diff_ce_loss_lambda > 0:
pred_indices_list = pred_indices.long().detach().cpu().numpy()
gt_indices_list = gt_indices.long().detach().cpu().numpy()
mask_list = batch["mask"].detach().cpu().numpy()
for i in range(pred_indices_list.shape[0]):
pred_acc = np.sum(
(pred_indices_list[i] == gt_indices_list[i]) * mask_list
) / np.sum(mask_list)
valid_losses["pred_acc_{}".format(str(i))] = pred_acc
return (total_loss.item(), valid_losses, valid_stats)
# def _train_epoch(self):
# ...
|