File size: 13,223 Bytes
4300fed
 
 
 
 
 
 
 
 
 
 
7af4264
 
 
4300fed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7af4264
 
4300fed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7af4264
4300fed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7af4264
 
 
4300fed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7af4264
4300fed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
import os
import glob
import argparse
import logging
import json
import subprocess
import numpy as np
from scipy.io.wavfile import read
import torch
import torchaudio
import librosa
from melo.text import cleaned_text_to_sequence, get_bert
from melo.text.cleaner import clean_text
from melo import commons

MATPLOTLIB_FLAG = False

logger = logging.getLogger(__name__)



def get_text_for_tts_infer(text, language_str, hps, device, symbol_to_id=None):
    norm_text, phone, tone, word2ph = clean_text(text, language_str)
    phone, tone, language = cleaned_text_to_sequence(phone, tone, language_str, symbol_to_id)

    if hps.data.add_blank:
        phone = commons.intersperse(phone, 0)
        tone = commons.intersperse(tone, 0)
        language = commons.intersperse(language, 0)
        for i in range(len(word2ph)):
            word2ph[i] = word2ph[i] * 2
        word2ph[0] += 1

    if getattr(hps.data, "disable_bert", False):
        bert = torch.zeros(1024, len(phone))
        ja_bert = torch.zeros(768, len(phone))
    else:
        bert = get_bert(norm_text, word2ph, language_str, device)
        del word2ph
        assert bert.shape[-1] == len(phone), phone

        if language_str == "ZH":
            bert = bert
            ja_bert = torch.zeros(768, len(phone))
        elif language_str in ["JP", "EN", "ZH_MIX_EN", 'KR', 'SP', 'ES', 'FR', 'DE', 'RU']:
            ja_bert = bert
            bert = torch.zeros(1024, len(phone))
        else:
            raise NotImplementedError()

    assert bert.shape[-1] == len(
        phone
    ), f"Bert seq len {bert.shape[-1]} != {len(phone)}"

    phone = torch.LongTensor(phone)
    tone = torch.LongTensor(tone)
    language = torch.LongTensor(language)
    return bert, ja_bert, phone, tone, language

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.get("iteration", 0)
    learning_rate = checkpoint_dict.get("learning_rate", 0.)
    if (
        optimizer is not None
        and not skip_optimizer
        and checkpoint_dict["optimizer"] is not None
    ):
        optimizer.load_state_dict(checkpoint_dict["optimizer"])
    elif optimizer is None and not skip_optimizer:
        # else:      Disable this line if Infer and resume checkpoint,then enable the line upper
        new_opt_dict = optimizer.state_dict()
        new_opt_dict_params = new_opt_dict["param_groups"][0]["params"]
        new_opt_dict["param_groups"] = checkpoint_dict["optimizer"]["param_groups"]
        new_opt_dict["param_groups"][0]["params"] = new_opt_dict_params
        optimizer.load_state_dict(new_opt_dict)

    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 "emb_g" not in 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 Exception as e:
            print(e)
            # For upgrading from the old version
            if "ja_bert_proj" in k:
                v = torch.zeros_like(v)
                logger.warn(
                    f"Seems you are using the old version of the model, the {k} is automatically set to zero for backward compatibility"
                )
            else:
                logger.error(f"{k} is not in the checkpoint")

            new_state_dict[k] = v

    if hasattr(model, "module"):
        model.module.load_state_dict(new_state_dict, strict=False)
    else:
        model.load_state_dict(new_state_dict, strict=False)

    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]
    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):
    sampling_rate, data = read(full_path)
    return torch.FloatTensor(data.astype(np.float32)), sampling_rate


def load_wav_to_torch_new(full_path):
    audio_norm, sampling_rate = torchaudio.load(full_path, frame_offset=0, num_frames=-1, normalize=True, channels_first=True)
    audio_norm = audio_norm.mean(dim=0)
    return audio_norm, sampling_rate

def load_wav_to_torch_librosa(full_path, sr):
    audio_norm, sampling_rate = librosa.load(full_path, sr=sr, mono=True)
    return torch.FloatTensor(audio_norm.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_hparams(init=True):
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "-c",
        "--config",
        type=str,
        default="./configs/base.json",
        help="JSON file for configuration",
    )
    parser.add_argument('--local_rank', type=int, default=0)
    parser.add_argument('--world-size', type=int, default=1)
    parser.add_argument('--port', type=int, default=10000)
    parser.add_argument("-m", "--model", type=str, required=True, help="Model name")
    parser.add_argument('--pretrain_G', type=str, default=None,
                            help='pretrain model')
    parser.add_argument('--pretrain_D', type=str, default=None,
                            help='pretrain model D')
    parser.add_argument('--pretrain_dur', type=str, default=None,
                            help='pretrain model duration')

    args = parser.parse_args()
    model_dir = os.path.join("./logs", args.model)

    os.makedirs(model_dir, exist_ok=True)

    config_path = args.config
    config_save_path = os.path.join(model_dir, "config.json")
    if init:
        with open(config_path, "r") as f:
            data = f.read()
        with open(config_save_path, "w") as f:
            f.write(data)
    else:
        with open(config_save_path, "r") as f:
            data = f.read()
    config = json.loads(data)

    hparams = HParams(**config)
    hparams.model_dir = model_dir
    hparams.pretrain_G = args.pretrain_G
    hparams.pretrain_D = args.pretrain_D
    hparams.pretrain_dur = args.pretrain_dur
    hparams.port = args.port
    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))
    ]

    def name_key(_f):
        return int(re.compile("._(\\d+)\\.pth").match(_f).group(1))

    def time_key(_f):
        return os.path.getmtime(os.path.join(path_to_models, _f))

    sort_key = time_key if sort_by_time else name_key

    def x_sorted(_x):
        return 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])
    ]

    def del_info(fn):
        return logger.info(f".. Free up space by deleting ckpt {fn}")

    def del_routine(x):
        return [os.remove(x), del_info(x)]

    [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", encoding="utf-8") 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", encoding="utf-8") 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, exist_ok=True)
    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__()