Spaces:
Sleeping
Sleeping
File size: 10,858 Bytes
6e584e5 3e23daa 6e584e5 |
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 |
import nltk
nltk.download('punkt')
nltk.download('punkt_tab')
import torch
torch.manual_seed(0)
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True
import os
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()
import phonemizer
from Utils.PLBERT.util import load_plbert
from Modules.diffusion.sampler import DiffusionSampler, ADPM2Sampler, KarrasSchedule
class STTS2:
def __init__(self, config_path, model_folder):
torch.manual_seed(0)
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True
random.seed(0)
np.random.seed(0)
self.device = 'cuda' if torch.cuda.is_available() else 'cpu'
self.textcleaner = TextCleaner()
self.to_mel = torchaudio.transforms.MelSpectrogram(
n_mels=80, n_fft=2048, win_length=1200, hop_length=300)
self.mean, self.std = -4, 4
self.global_phonemizer = phonemizer.backend.EspeakBackend(language='fr-fr', preserve_punctuation=True, with_stress=True)
config = yaml.safe_load(open(config_path))
self.text_aligner = load_ASR_models(config.get('ASR_path', False), config.get('ASR_config', False))
self.pitch_extractor = load_F0_models(config.get('F0_path', False))
self.plbert = load_plbert(config.get('PLBERT_dir', False))
self.model_params = recursive_munch(config['model_params'])
self.model = build_model(self.model_params, self.text_aligner, self.pitch_extractor, self.plbert)
_ = [self.model[key].eval() for key in self.model]
_ = [self.model[key].to(self.device) for key in self.model]
files = [f for f in os.listdir(model_folder+"/") if f.endswith('.pth')]
sorted_files = sorted(files, key=lambda x: int(x.split('_')[-1].split('.')[0]))
print("sorted_files:", sorted_files)
params_whole = torch.load(model_folder+"/" + sorted_files[-1], map_location='cpu')
params = params_whole['net']
for key in self.model:
if key in params:
print('%s loaded' % key)
try:
self.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
self.model[key].load_state_dict(new_state_dict, strict=False)
_ = [self.model[key].eval() for key in self.model]
self.sampler = DiffusionSampler(
self.model.diffusion.diffusion,
sampler=ADPM2Sampler(),
sigma_schedule=KarrasSchedule(sigma_min=0.0001, sigma_max=3.0, rho=9.0),
clamp=False
)
def length_to_mask(self, 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(self, wave):
wave_tensor = torch.from_numpy(wave).float()
mel_tensor = self.to_mel(wave_tensor)
mel_tensor = (torch.log(1e-5 + mel_tensor.unsqueeze(0)) - self.mean) / self.std
return mel_tensor
def compute_style(self, 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 = self.preprocess(audio).to(self.device)
with torch.no_grad():
ref_s = self.model.style_encoder(mel_tensor.unsqueeze(1))
ref_p = self.model.predictor_encoder(mel_tensor.unsqueeze(1))
return torch.cat([ref_s, ref_p], dim=1)
def inference(self, text, ref_s, alpha=0.3, beta=0.7, diffusion_steps=5, embedding_scale=1):
text = text.strip()
ps = self.global_phonemizer.phonemize([text])
ps = word_tokenize(ps[0])
ps = ' '.join(ps)
tokens = self.textcleaner(ps)
tokens.insert(0, 0)
tokens = torch.LongTensor(tokens).to(self.device).unsqueeze(0)
print("tokens:", tokens)
with torch.no_grad():
input_lengths = torch.LongTensor([tokens.shape[-1]]).to(self.device)
text_mask = self.length_to_mask(input_lengths).to(self.device)
t_en = self.model.text_encoder(tokens, input_lengths, text_mask)
bert_dur = self.model.bert(tokens, attention_mask=(~text_mask).int())
d_en = self.model.bert_encoder(bert_dur).transpose(-1, -2)
s_pred = self.sampler(
noise=torch.randn((1, 256)).unsqueeze(1).to(self.device),
embedding=bert_dur,
embedding_scale=embedding_scale,
features=ref_s,
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 = self.model.predictor.text_encoder(d_en, s, input_lengths, text_mask)
x, _ = self.model.predictor.lstm(d)
duration = self.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)
en = (d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(self.device))
if self.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 = self.model.predictor.F0Ntrain(en, s)
asr = (t_en @ pred_aln_trg.unsqueeze(0).to(self.device))
if self.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 = self.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 laterclass STTS2:
def length_to_mask(self, 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(self, wave):
wave_tensor = torch.from_numpy(wave).float()
mel_tensor = self.to_mel(wave_tensor)
mel_tensor = (torch.log(1e-5 + mel_tensor.unsqueeze(0)) - self.mean) / self.std
return mel_tensor
def compute_style(self, 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 = self.preprocess(audio).to(self.device)
with torch.no_grad():
ref_s = self.model.style_encoder(mel_tensor.unsqueeze(1))
ref_p = self.model.predictor_encoder(mel_tensor.unsqueeze(1))
return torch.cat([ref_s, ref_p], dim=1)
def inference(self, text, ref_s, alpha=0.3, beta=0.7, diffusion_steps=5, embedding_scale=1):
text = text.strip()
ps = self.global_phonemizer.phonemize([text])
ps[0] = ps[0].replace("(en)", "").replace("(fr)", "")
ps = word_tokenize(ps[0])
ps = ' '.join(ps)
tokens = self.textcleaner(ps)
tokens.insert(0, 0)
tokens = torch.LongTensor(tokens).to(self.device).unsqueeze(0)
with torch.no_grad():
input_lengths = torch.LongTensor([tokens.shape[-1]]).to(self.device)
text_mask = self.length_to_mask(input_lengths).to(self.device)
t_en = self.model.text_encoder(tokens, input_lengths, text_mask)
bert_dur = self.model.bert(tokens, attention_mask=(~text_mask).int())
d_en = self.model.bert_encoder(bert_dur).transpose(-1, -2)
s_pred = self.sampler(
noise=torch.randn((1, 256)).unsqueeze(1).to(self.device),
embedding=bert_dur,
embedding_scale=embedding_scale,
features=ref_s,
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 = self.model.predictor.text_encoder(d_en, s, input_lengths, text_mask)
x, _ = self.model.predictor.lstm(d)
duration = self.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)
en = (d.transpose(-1, -2) @ pred_aln_trg.unsqueeze(0).to(self.device))
if self.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 = self.model.predictor.F0Ntrain(en, s)
asr = (t_en @ pred_aln_trg.unsqueeze(0).to(self.device))
if self.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 = self.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
|