File size: 10,738 Bytes
26be912 8373106 26be912 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 |
import os
import glob
import sys
import argparse
import logging
import json
import subprocess
import traceback
import librosa
import numpy as np
from scipy.io.wavfile import read
import torch
import logging
logging.getLogger("numba").setLevel(logging.ERROR)
logging.getLogger("matplotlib").setLevel(logging.ERROR)
MATPLOTLIB_FLAG = False
# logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)
logger = logging
def load_checkpoint(checkpoint_path, model, optimizer=None, skip_optimizer=False):
assert os.path.isfile(checkpoint_path)
checkpoint_dict = torch.load(checkpoint_path, map_location="cpu")
iteration = checkpoint_dict["iteration"]
learning_rate = checkpoint_dict["learning_rate"]
if (
optimizer is not None
and not skip_optimizer
and checkpoint_dict["optimizer"] is not None
):
optimizer.load_state_dict(checkpoint_dict["optimizer"])
saved_state_dict = checkpoint_dict["model"]
if hasattr(model, "module"):
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
new_state_dict = {}
for k, v in state_dict.items():
try:
# assert "quantizer" not in k
# print("load", k)
new_state_dict[k] = saved_state_dict[k]
assert saved_state_dict[k].shape == v.shape, (
saved_state_dict[k].shape,
v.shape,
)
except:
traceback.print_exc()
print(
"error, %s is not in the checkpoint" % k
) # shape不对也会,比如text_embedding当cleaner修改时
new_state_dict[k] = v
if hasattr(model, "module"):
model.module.load_state_dict(new_state_dict)
else:
model.load_state_dict(new_state_dict)
print("load ")
logger.info(
"Loaded checkpoint '{}' (iteration {})".format(checkpoint_path, iteration)
)
return model, optimizer, learning_rate, iteration
def save_checkpoint(model, optimizer, learning_rate, iteration, checkpoint_path):
logger.info(
"Saving model and optimizer state at iteration {} to {}".format(
iteration, checkpoint_path
)
)
if hasattr(model, "module"):
state_dict = model.module.state_dict()
else:
state_dict = model.state_dict()
torch.save(
{
"model": state_dict,
"iteration": iteration,
"optimizer": optimizer.state_dict(),
"learning_rate": learning_rate,
},
checkpoint_path,
)
def summarize(
writer,
global_step,
scalars={},
histograms={},
images={},
audios={},
audio_sampling_rate=22050,
):
for k, v in scalars.items():
writer.add_scalar(k, v, global_step)
for k, v in histograms.items():
writer.add_histogram(k, v, global_step)
for k, v in images.items():
writer.add_image(k, v, global_step, dataformats="HWC")
for k, v in audios.items():
writer.add_audio(k, v, global_step, audio_sampling_rate)
def latest_checkpoint_path(dir_path, regex="G_*.pth"):
f_list = glob.glob(os.path.join(dir_path, regex))
f_list.sort(key=lambda f: int("".join(filter(str.isdigit, f))))
x = f_list[-1]
print(x)
return x
def plot_spectrogram_to_numpy(spectrogram):
global MATPLOTLIB_FLAG
if not MATPLOTLIB_FLAG:
import matplotlib
matplotlib.use("Agg")
MATPLOTLIB_FLAG = True
mpl_logger = logging.getLogger("matplotlib")
mpl_logger.setLevel(logging.WARNING)
import matplotlib.pylab as plt
import numpy as np
fig, ax = plt.subplots(figsize=(10, 2))
im = ax.imshow(spectrogram, aspect="auto", origin="lower", interpolation="none")
plt.colorbar(im, ax=ax)
plt.xlabel("Frames")
plt.ylabel("Channels")
plt.tight_layout()
fig.canvas.draw()
data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
plt.close()
return data
def plot_alignment_to_numpy(alignment, info=None):
global MATPLOTLIB_FLAG
if not MATPLOTLIB_FLAG:
import matplotlib
matplotlib.use("Agg")
MATPLOTLIB_FLAG = True
mpl_logger = logging.getLogger("matplotlib")
mpl_logger.setLevel(logging.WARNING)
import matplotlib.pylab as plt
import numpy as np
fig, ax = plt.subplots(figsize=(6, 4))
im = ax.imshow(
alignment.transpose(), aspect="auto", origin="lower", interpolation="none"
)
fig.colorbar(im, ax=ax)
xlabel = "Decoder timestep"
if info is not None:
xlabel += "\n\n" + info
plt.xlabel(xlabel)
plt.ylabel("Encoder timestep")
plt.tight_layout()
fig.canvas.draw()
data = np.fromstring(fig.canvas.tostring_rgb(), dtype=np.uint8, sep="")
data = data.reshape(fig.canvas.get_width_height()[::-1] + (3,))
plt.close()
return data
def load_wav_to_torch(full_path):
data, sampling_rate = librosa.load(full_path, sr=None)
return torch.FloatTensor(data), sampling_rate
def load_filepaths_and_text(filename, split="|"):
with open(filename, encoding="utf-8") as f:
filepaths_and_text = [line.strip().split(split) for line in f]
return filepaths_and_text
def get_hparams(init=True, stage=1):
parser = argparse.ArgumentParser()
parser.add_argument(
"-c",
"--config",
type=str,
default="./configs/s2.json",
help="JSON file for configuration",
)
parser.add_argument(
"-p", "--pretrain", type=str, required=False, default=None, help="pretrain dir"
)
parser.add_argument(
"-rs",
"--resume_step",
type=int,
required=False,
default=None,
help="resume step",
)
# parser.add_argument('-e', '--exp_dir', type=str, required=False,default=None,help='experiment directory')
# parser.add_argument('-g', '--pretrained_s2G', type=str, required=False,default=None,help='pretrained sovits gererator weights')
# parser.add_argument('-d', '--pretrained_s2D', type=str, required=False,default=None,help='pretrained sovits discriminator weights')
args = parser.parse_args()
config_path = args.config
with open(config_path, "r") as f:
data = f.read()
config = json.loads(data)
hparams = HParams(**config)
hparams.pretrain = args.pretrain
hparams.resume_step = args.resume_step
# hparams.data.exp_dir = args.exp_dir
if stage == 1:
model_dir = hparams.s1_ckpt_dir
else:
model_dir = hparams.s2_ckpt_dir
config_save_path = os.path.join(model_dir, "config.json")
if not os.path.exists(model_dir):
os.makedirs(model_dir)
with open(config_save_path, "w") as f:
f.write(data)
return hparams
def clean_checkpoints(path_to_models="logs/44k/", n_ckpts_to_keep=2, sort_by_time=True):
"""Freeing up space by deleting saved ckpts
Arguments:
path_to_models -- Path to the model directory
n_ckpts_to_keep -- Number of ckpts to keep, excluding G_0.pth and D_0.pth
sort_by_time -- True -> chronologically delete ckpts
False -> lexicographically delete ckpts
"""
import re
ckpts_files = [
f
for f in os.listdir(path_to_models)
if os.path.isfile(os.path.join(path_to_models, f))
]
name_key = lambda _f: int(re.compile("._(\d+)\.pth").match(_f).group(1))
time_key = lambda _f: os.path.getmtime(os.path.join(path_to_models, _f))
sort_key = time_key if sort_by_time else name_key
x_sorted = lambda _x: sorted(
[f for f in ckpts_files if f.startswith(_x) and not f.endswith("_0.pth")],
key=sort_key,
)
to_del = [
os.path.join(path_to_models, fn)
for fn in (x_sorted("G")[:-n_ckpts_to_keep] + x_sorted("D")[:-n_ckpts_to_keep])
]
del_info = lambda fn: logger.info(f".. Free up space by deleting ckpt {fn}")
del_routine = lambda x: [os.remove(x), del_info(x)]
rs = [del_routine(fn) for fn in to_del]
def get_hparams_from_dir(model_dir):
config_save_path = os.path.join(model_dir, "config.json")
with open(config_save_path, "r") as f:
data = f.read()
config = json.loads(data)
hparams = HParams(**config)
hparams.model_dir = model_dir
return hparams
def get_hparams_from_file(config_path):
with open(config_path, "r") as f:
data = f.read()
config = json.loads(data)
hparams = HParams(**config)
return hparams
def check_git_hash(model_dir):
source_dir = os.path.dirname(os.path.realpath(__file__))
if not os.path.exists(os.path.join(source_dir, ".git")):
logger.warn(
"{} is not a git repository, therefore hash value comparison will be ignored.".format(
source_dir
)
)
return
cur_hash = subprocess.getoutput("git rev-parse HEAD")
path = os.path.join(model_dir, "githash")
if os.path.exists(path):
saved_hash = open(path).read()
if saved_hash != cur_hash:
logger.warn(
"git hash values are different. {}(saved) != {}(current)".format(
saved_hash[:8], cur_hash[:8]
)
)
else:
open(path, "w").write(cur_hash)
def get_logger(model_dir, filename="train.log"):
global logger
logger = logging.getLogger(os.path.basename(model_dir))
logger.setLevel(logging.DEBUG)
formatter = logging.Formatter("%(asctime)s\t%(name)s\t%(levelname)s\t%(message)s")
if not os.path.exists(model_dir):
os.makedirs(model_dir)
h = logging.FileHandler(os.path.join(model_dir, filename))
h.setLevel(logging.DEBUG)
h.setFormatter(formatter)
logger.addHandler(h)
return logger
class HParams:
def __init__(self, **kwargs):
for k, v in kwargs.items():
if type(v) == dict:
v = HParams(**v)
self[k] = v
def keys(self):
return self.__dict__.keys()
def items(self):
return self.__dict__.items()
def values(self):
return self.__dict__.values()
def __len__(self):
return len(self.__dict__)
def __getitem__(self, key):
return getattr(self, key)
def __setitem__(self, key, value):
return setattr(self, key, value)
def __contains__(self, key):
return key in self.__dict__
def __repr__(self):
return self.__dict__.__repr__()
if __name__ == "__main__":
print(
load_wav_to_torch(
"/home/fish/wenetspeech/dataset_vq/Y0000022499_wHFSeHEx9CM/S00261.flac"
)
)
|