157 lines
4.5 KiB
Python
157 lines
4.5 KiB
Python
import glob
|
|
import logging
|
|
import os
|
|
import re
|
|
import subprocess
|
|
|
|
import numpy as np
|
|
import torch
|
|
from scipy.io.wavfile import read
|
|
|
|
from style_bert_vits2.logging import logger
|
|
from style_bert_vits2.models.utils import checkpoints # type: ignore
|
|
from style_bert_vits2.models.utils import safetensors # type: ignore
|
|
|
|
|
|
MATPLOTLIB_FLAG = False
|
|
|
|
|
|
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 is_resuming(dir_path):
|
|
# JP-ExtraバージョンではDURがなくWDがあったり変わるため、Gのみで判断する
|
|
g_list = glob.glob(os.path.join(dir_path, "G_*.pth"))
|
|
# d_list = glob.glob(os.path.join(dir_path, "D_*.pth"))
|
|
# dur_list = glob.glob(os.path.join(dir_path, "DUR_*.pth"))
|
|
return len(g_list) > 0
|
|
|
|
|
|
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):
|
|
sampling_rate, data = read(full_path)
|
|
return torch.FloatTensor(data.astype(np.float32)), 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_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
|
|
|
|
|
|
def get_steps(model_path):
|
|
matches = re.findall(r"\d+", model_path)
|
|
return matches[-1] if matches else None
|
|
|
|
|
|
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.warning(
|
|
"{} 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.warning(
|
|
"git hash values are different. {}(saved) != {}(current)".format(
|
|
saved_hash[:8], cur_hash[:8]
|
|
)
|
|
)
|
|
else:
|
|
open(path, "w").write(cur_hash)
|