File size: 13,052 Bytes
635f007
 
675a486
635f007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
675a486
 
 
635f007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
675a486
635f007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
675a486
635f007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
675a486
635f007
 
 
 
 
 
 
 
675a486
635f007
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from cached_path import cached_path

# from dp.phonemizer import Phonemizer
print("NLTK")
import nltk
nltk.download('punkt')
print("SCIPY")
from scipy.io.wavfile import write
print("TORCH STUFF")
import torch
print("START")
torch.manual_seed(0)
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True

import random
random.seed(0)

import numpy as np
np.random.seed(0)

# load packages
import time
import random
import yaml
from munch import Munch
import numpy as np
import torch
from torch import nn
import torch.nn.functional as F
import torchaudio
import librosa
from nltk.tokenize import word_tokenize

from models import *
from utils import *
from text_utils import TextCleaner
textclenaer = TextCleaner()


to_mel = torchaudio.transforms.MelSpectrogram(
    n_mels=80, n_fft=2048, win_length=1200, hop_length=300)
mean, std = -4, 4

def length_to_mask(lengths):
    mask = torch.arange(lengths.max()).unsqueeze(0).expand(lengths.shape[0], -1).type_as(lengths)
    mask = torch.gt(mask+1, lengths.unsqueeze(1))
    return mask

def preprocess(wave):
    wave_tensor = torch.from_numpy(wave).float()
    mel_tensor = to_mel(wave_tensor)
    mel_tensor = (torch.log(1e-5 + mel_tensor.unsqueeze(0)) - mean) / std
    return mel_tensor

def compute_style(path):
    wave, sr = librosa.load(path, sr=24000)
    audio, index = librosa.effects.trim(wave, top_db=30)
    if sr != 24000:
        audio = librosa.resample(audio, sr, 24000)
    mel_tensor = preprocess(audio).to(device)

    with torch.no_grad():
        ref_s = model.style_encoder(mel_tensor.unsqueeze(1))
        ref_p = model.predictor_encoder(mel_tensor.unsqueeze(1))

    return torch.cat([ref_s, ref_p], dim=1)

device = 'cpu'
if torch.cuda.is_available():
    device = 'cuda'
elif torch.backends.mps.is_available():
    print("MPS would be available but cannot be used rn")
    # device = 'mps'

import phonemizer
global_phonemizer = phonemizer.backend.EspeakBackend(language='en-us', preserve_punctuation=True,  with_stress=True)
# phonemizer = Phonemizer.from_checkpoint(str(cached_path('https://public-asai-dl-models.s3.eu-central-1.amazonaws.com/DeepPhonemizer/en_us_cmudict_ipa_forward.pt')))


# config = yaml.safe_load(open("Models/LibriTTS/config.yml"))
config = yaml.safe_load(open(str(cached_path("hf://yl4579/StyleTTS2-LibriTTS/Models/LibriTTS/config.yml"))))

# load pretrained ASR model
ASR_config = config.get('ASR_config', False)
ASR_path = config.get('ASR_path', False)
text_aligner = load_ASR_models(ASR_path, ASR_config)

# load pretrained F0 model
F0_path = config.get('F0_path', False)
pitch_extractor = load_F0_models(F0_path)

# load BERT model
from Utils.PLBERT.util import load_plbert
BERT_path = config.get('PLBERT_dir', False)
plbert = load_plbert(BERT_path)

model_params = recursive_munch(config['model_params'])
model = build_model(model_params, text_aligner, pitch_extractor, plbert)
_ = [model[key].eval() for key in model]
_ = [model[key].to(device) for key in model]

# params_whole = torch.load("Models/LibriTTS/epochs_2nd_00020.pth", map_location='cpu')
params_whole = torch.load(str(cached_path("hf://yl4579/StyleTTS2-LibriTTS/Models/LibriTTS/epochs_2nd_00020.pth")), map_location='cpu')
params = params_whole['net']

for key in model:
    if key in params:
        print('%s loaded' % key)
        try:
            model[key].load_state_dict(params[key])
        except:
            from collections import OrderedDict
            state_dict = params[key]
            new_state_dict = OrderedDict()
            for k, v in state_dict.items():
                name = k[7:] # remove `module.`
                new_state_dict[name] = v
            # load params
            model[key].load_state_dict(new_state_dict, strict=False)
#             except:
#                 _load(params[key], model[key])
_ = [model[key].eval() for key in model]

from Modules.diffusion.sampler import DiffusionSampler, ADPM2Sampler, KarrasSchedule

sampler = DiffusionSampler(
    model.diffusion.diffusion,
    sampler=ADPM2Sampler(),
    sigma_schedule=KarrasSchedule(sigma_min=0.0001, sigma_max=3.0, rho=9.0), # empirical parameters
    clamp=False
)

def inference(text, ref_s, alpha = 0.3, beta = 0.7, diffusion_steps=5, embedding_scale=1):
    text = text.strip()
    ps = global_phonemizer.phonemize([text])
    ps = word_tokenize(ps[0])
    ps = ' '.join(ps)
    tokens = textclenaer(ps)
    tokens.insert(0, 0)
    tokens = torch.LongTensor(tokens).to(device).unsqueeze(0)

    with torch.no_grad():
        input_lengths = torch.LongTensor([tokens.shape[-1]]).to(device)
        text_mask = length_to_mask(input_lengths).to(device)

        t_en = model.text_encoder(tokens, input_lengths, text_mask)
        bert_dur = model.bert(tokens, attention_mask=(~text_mask).int())
        d_en = model.bert_encoder(bert_dur).transpose(-1, -2)

        s_pred = sampler(noise = torch.randn((1, 256)).unsqueeze(1).to(device),
                                          embedding=bert_dur,
                                          embedding_scale=embedding_scale,
                                            features=ref_s, # reference from the same speaker as the embedding
                                             num_steps=diffusion_steps).squeeze(1)


        s = s_pred[:, 128:]
        ref = s_pred[:, :128]

        ref = alpha * ref + (1 - alpha)  * ref_s[:, :128]
        s = beta * s + (1 - beta)  * ref_s[:, 128:]

        d = model.predictor.text_encoder(d_en,
                                         s, input_lengths, text_mask)

        x, _ = model.predictor.lstm(d)
        duration = model.predictor.duration_proj(x)

        duration = torch.sigmoid(duration).sum(axis=-1)
        pred_dur = torch.round(duration.squeeze()).clamp(min=1)


        pred_aln_trg = torch.zeros(input_lengths, int(pred_dur.sum().data))
        c_frame = 0
        for i in range(pred_aln_trg.size(0)):
            pred_aln_trg[i, c_frame:c_frame + int(pred_dur[i].data)] = 1
            c_frame += int(pred_dur[i].data)

        # encode prosody
        en = (d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(device))
        if model_params.decoder.type == "hifigan":
            asr_new = torch.zeros_like(en)
            asr_new[:, :, 0] = en[:, :, 0]
            asr_new[:, :, 1:] = en[:, :, 0:-1]
            en = asr_new

        F0_pred, N_pred = model.predictor.F0Ntrain(en, s)

        asr = (t_en @ pred_aln_trg.unsqueeze(0).to(device))
        if model_params.decoder.type == "hifigan":
            asr_new = torch.zeros_like(asr)
            asr_new[:, :, 0] = asr[:, :, 0]
            asr_new[:, :, 1:] = asr[:, :, 0:-1]
            asr = asr_new

        out = model.decoder(asr,
                                F0_pred, N_pred, ref.squeeze().unsqueeze(0))


    return out.squeeze().cpu().numpy()[..., :-50] # weird pulse at the end of the model, need to be fixed later

def LFinference(text, s_prev, ref_s, alpha = 0.3, beta = 0.7, t = 0.7, diffusion_steps=5, embedding_scale=1):
  text = text.strip()
  ps = global_phonemizer.phonemize([text])
  ps = word_tokenize(ps[0])
  ps = ' '.join(ps)
  ps = ps.replace('``', '"')
  ps = ps.replace("''", '"')

  tokens = textclenaer(ps)
  tokens.insert(0, 0)
  tokens = torch.LongTensor(tokens).to(device).unsqueeze(0)

  with torch.no_grad():
      input_lengths = torch.LongTensor([tokens.shape[-1]]).to(device)
      text_mask = length_to_mask(input_lengths).to(device)

      t_en = model.text_encoder(tokens, input_lengths, text_mask)
      bert_dur = model.bert(tokens, attention_mask=(~text_mask).int())
      d_en = model.bert_encoder(bert_dur).transpose(-1, -2)

      s_pred = sampler(noise = torch.randn((1, 256)).unsqueeze(1).to(device),
                                        embedding=bert_dur,
                                        embedding_scale=embedding_scale,
                                          features=ref_s, # reference from the same speaker as the embedding
                                            num_steps=diffusion_steps).squeeze(1)

      if s_prev is not None:
          # convex combination of previous and current style
          s_pred = t * s_prev + (1 - t) * s_pred

      s = s_pred[:, 128:]
      ref = s_pred[:, :128]

      ref = alpha * ref + (1 - alpha)  * ref_s[:, :128]
      s = beta * s + (1 - beta)  * ref_s[:, 128:]

      s_pred = torch.cat([ref, s], dim=-1)

      d = model.predictor.text_encoder(d_en,
                                        s, input_lengths, text_mask)

      x, _ = model.predictor.lstm(d)
      duration = model.predictor.duration_proj(x)

      duration = torch.sigmoid(duration).sum(axis=-1)
      pred_dur = torch.round(duration.squeeze()).clamp(min=1)


      pred_aln_trg = torch.zeros(input_lengths, int(pred_dur.sum().data))
      c_frame = 0
      for i in range(pred_aln_trg.size(0)):
          pred_aln_trg[i, c_frame:c_frame + int(pred_dur[i].data)] = 1
          c_frame += int(pred_dur[i].data)

      # encode prosody
      en = (d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(device))
      if model_params.decoder.type == "hifigan":
          asr_new = torch.zeros_like(en)
          asr_new[:, :, 0] = en[:, :, 0]
          asr_new[:, :, 1:] = en[:, :, 0:-1]
          en = asr_new

      F0_pred, N_pred = model.predictor.F0Ntrain(en, s)

      asr = (t_en @ pred_aln_trg.unsqueeze(0).to(device))
      if model_params.decoder.type == "hifigan":
          asr_new = torch.zeros_like(asr)
          asr_new[:, :, 0] = asr[:, :, 0]
          asr_new[:, :, 1:] = asr[:, :, 0:-1]
          asr = asr_new

      out = model.decoder(asr,
                              F0_pred, N_pred, ref.squeeze().unsqueeze(0))


  return out.squeeze().cpu().numpy()[..., :-100], s_pred # weird pulse at the end of the model, need to be fixed later

def STinference(text, ref_s, ref_text, alpha = 0.3, beta = 0.7, diffusion_steps=5, embedding_scale=1):
    text = text.strip()
    ps = global_phonemizer.phonemize([text])
    ps = word_tokenize(ps[0])
    ps = ' '.join(ps)

    tokens = textclenaer(ps)
    tokens.insert(0, 0)
    tokens = torch.LongTensor(tokens).to(device).unsqueeze(0)

    ref_text = ref_text.strip()
    ps = global_phonemizer.phonemize([ref_text])
    ps = word_tokenize(ps[0])
    ps = ' '.join(ps)

    ref_tokens = textclenaer(ps)
    ref_tokens.insert(0, 0)
    ref_tokens = torch.LongTensor(ref_tokens).to(device).unsqueeze(0)


    with torch.no_grad():
        input_lengths = torch.LongTensor([tokens.shape[-1]]).to(device)
        text_mask = length_to_mask(input_lengths).to(device)

        t_en = model.text_encoder(tokens, input_lengths, text_mask)
        bert_dur = model.bert(tokens, attention_mask=(~text_mask).int())
        d_en = model.bert_encoder(bert_dur).transpose(-1, -2)

        ref_input_lengths = torch.LongTensor([ref_tokens.shape[-1]]).to(device)
        ref_text_mask = length_to_mask(ref_input_lengths).to(device)
        ref_bert_dur = model.bert(ref_tokens, attention_mask=(~ref_text_mask).int())
        s_pred = sampler(noise = torch.randn((1, 256)).unsqueeze(1).to(device),
                                          embedding=bert_dur,
                                          embedding_scale=embedding_scale,
                                            features=ref_s, # reference from the same speaker as the embedding
                                             num_steps=diffusion_steps).squeeze(1)


        s = s_pred[:, 128:]
        ref = s_pred[:, :128]

        ref = alpha * ref + (1 - alpha)  * ref_s[:, :128]
        s = beta * s + (1 - beta)  * ref_s[:, 128:]

        d = model.predictor.text_encoder(d_en,
                                         s, input_lengths, text_mask)

        x, _ = model.predictor.lstm(d)
        duration = model.predictor.duration_proj(x)

        duration = torch.sigmoid(duration).sum(axis=-1)
        pred_dur = torch.round(duration.squeeze()).clamp(min=1)


        pred_aln_trg = torch.zeros(input_lengths, int(pred_dur.sum().data))
        c_frame = 0
        for i in range(pred_aln_trg.size(0)):
            pred_aln_trg[i, c_frame:c_frame + int(pred_dur[i].data)] = 1
            c_frame += int(pred_dur[i].data)

        # encode prosody
        en = (d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(device))
        if model_params.decoder.type == "hifigan":
            asr_new = torch.zeros_like(en)
            asr_new[:, :, 0] = en[:, :, 0]
            asr_new[:, :, 1:] = en[:, :, 0:-1]
            en = asr_new

        F0_pred, N_pred = model.predictor.F0Ntrain(en, s)

        asr = (t_en @ pred_aln_trg.unsqueeze(0).to(device))
        if model_params.decoder.type == "hifigan":
            asr_new = torch.zeros_like(asr)
            asr_new[:, :, 0] = asr[:, :, 0]
            asr_new[:, :, 1:] = asr[:, :, 0:-1]
            asr = asr_new

        out = model.decoder(asr,
                                F0_pred, N_pred, ref.squeeze().unsqueeze(0))


    return out.squeeze().cpu().numpy()[..., :-50] # weird pulse at the end of the model, need to be fixed later