orz99's picture
Duplicate from lj1995/VoiceConversionWebUI
fe2871c
import math,pdb,os
from time import time as ttime
import torch
from torch import nn
from torch.nn import functional as F
from infer_pack import modules
from infer_pack import attentions
from torch.nn import Conv1d, ConvTranspose1d, AvgPool1d, Conv2d
from torch.nn.utils import weight_norm, remove_weight_norm, spectral_norm
from infer_pack.commons import init_weights
import numpy as np
from infer_pack import commons
class TextEncoder256(nn.Module):
def __init__(
self, out_channels, hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout, f0=True ):
super().__init__()
self.out_channels = out_channels
self.hidden_channels = hidden_channels
self.filter_channels = filter_channels
self.n_heads = n_heads
self.n_layers = n_layers
self.kernel_size = kernel_size
self.p_dropout = p_dropout
self.emb_phone = nn.Linear(256, hidden_channels)
self.lrelu=nn.LeakyReLU(0.1,inplace=True)
if(f0==True):
self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
self.encoder = attentions.Encoder(
hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
)
self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
def forward(self, phone, pitch, lengths):
if(pitch==None):
x = self.emb_phone(phone)
else:
x = self.emb_phone(phone) + self.emb_pitch(pitch)
x = x * math.sqrt(self.hidden_channels) # [b, t, h]
x=self.lrelu(x)
x = torch.transpose(x, 1, -1) # [b, h, t]
x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
x.dtype
)
x = self.encoder(x * x_mask, x_mask)
stats = self.proj(x) * x_mask
m, logs = torch.split(stats, self.out_channels, dim=1)
return m, logs, x_mask
class TextEncoder256km(nn.Module):
def __init__(
self, out_channels, hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout, f0=True ):
super().__init__()
self.out_channels = out_channels
self.hidden_channels = hidden_channels
self.filter_channels = filter_channels
self.n_heads = n_heads
self.n_layers = n_layers
self.kernel_size = kernel_size
self.p_dropout = p_dropout
# self.emb_phone = nn.Linear(256, hidden_channels)
self.emb_phone = nn.Embedding(500, hidden_channels)
self.lrelu=nn.LeakyReLU(0.1,inplace=True)
if(f0==True):
self.emb_pitch = nn.Embedding(256, hidden_channels) # pitch 256
self.encoder = attentions.Encoder(
hidden_channels, filter_channels, n_heads, n_layers, kernel_size, p_dropout
)
self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
def forward(self, phone, pitch, lengths):
if(pitch==None):
x = self.emb_phone(phone)
else:
x = self.emb_phone(phone) + self.emb_pitch(pitch)
x = x * math.sqrt(self.hidden_channels) # [b, t, h]
x=self.lrelu(x)
x = torch.transpose(x, 1, -1) # [b, h, t]
x_mask = torch.unsqueeze(commons.sequence_mask(lengths, x.size(2)), 1).to(
x.dtype
)
x = self.encoder(x * x_mask, x_mask)
stats = self.proj(x) * x_mask
m, logs = torch.split(stats, self.out_channels, dim=1)
return m, logs, x_mask
class ResidualCouplingBlock(nn.Module):
def __init__(
self,
channels,
hidden_channels,
kernel_size,
dilation_rate,
n_layers,
n_flows=4,
gin_channels=0,
):
super().__init__()
self.channels = channels
self.hidden_channels = hidden_channels
self.kernel_size = kernel_size
self.dilation_rate = dilation_rate
self.n_layers = n_layers
self.n_flows = n_flows
self.gin_channels = gin_channels
self.flows = nn.ModuleList()
for i in range(n_flows):
self.flows.append(
modules.ResidualCouplingLayer(
channels,
hidden_channels,
kernel_size,
dilation_rate,
n_layers,
gin_channels=gin_channels,
mean_only=True,
)
)
self.flows.append(modules.Flip())
def forward(self, x, x_mask, g=None, reverse=False):
if not reverse:
for flow in self.flows:
x, _ = flow(x, x_mask, g=g, reverse=reverse)
else:
for flow in reversed(self.flows):
x = flow(x, x_mask, g=g, reverse=reverse)
return x
def remove_weight_norm(self):
for i in range(self.n_flows):
self.flows[i * 2].remove_weight_norm()
class PosteriorEncoder(nn.Module):
def __init__(
self,
in_channels,
out_channels,
hidden_channels,
kernel_size,
dilation_rate,
n_layers,
gin_channels=0,
):
super().__init__()
self.in_channels = in_channels
self.out_channels = out_channels
self.hidden_channels = hidden_channels
self.kernel_size = kernel_size
self.dilation_rate = dilation_rate
self.n_layers = n_layers
self.gin_channels = gin_channels
self.pre = nn.Conv1d(in_channels, hidden_channels, 1)
self.enc = modules.WN(
hidden_channels,
kernel_size,
dilation_rate,
n_layers,
gin_channels=gin_channels,
)
self.proj = nn.Conv1d(hidden_channels, out_channels * 2, 1)
def forward(self, x, x_lengths, g=None):
x_mask = torch.unsqueeze(commons.sequence_mask(x_lengths, x.size(2)), 1).to(
x.dtype
)
x = self.pre(x) * x_mask
x = self.enc(x, x_mask, g=g)
stats = self.proj(x) * x_mask
m, logs = torch.split(stats, self.out_channels, dim=1)
z = (m + torch.randn_like(m) * torch.exp(logs)) * x_mask
return z, m, logs, x_mask
def remove_weight_norm(self):
self.enc.remove_weight_norm()
class Generator(torch.nn.Module):
def __init__(
self,
initial_channel,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
gin_channels=0,
):
super(Generator, self).__init__()
self.num_kernels = len(resblock_kernel_sizes)
self.num_upsamples = len(upsample_rates)
self.conv_pre = Conv1d(
initial_channel, upsample_initial_channel, 7, 1, padding=3
)
resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
self.ups = nn.ModuleList()
for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
self.ups.append(
weight_norm(
ConvTranspose1d(
upsample_initial_channel // (2**i),
upsample_initial_channel // (2 ** (i + 1)),
k,
u,
padding=(k - u) // 2,
)
)
)
self.resblocks = nn.ModuleList()
for i in range(len(self.ups)):
ch = upsample_initial_channel // (2 ** (i + 1))
for j, (k, d) in enumerate(
zip(resblock_kernel_sizes, resblock_dilation_sizes)
):
self.resblocks.append(resblock(ch, k, d))
self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
self.ups.apply(init_weights)
if gin_channels != 0:
self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
def forward(self, x, g=None):
x = self.conv_pre(x)
if g is not None:
x = x + self.cond(g)
for i in range(self.num_upsamples):
x = F.leaky_relu(x, modules.LRELU_SLOPE)
x = self.ups[i](x)
xs = None
for j in range(self.num_kernels):
if xs is None:
xs = self.resblocks[i * self.num_kernels + j](x)
else:
xs += self.resblocks[i * self.num_kernels + j](x)
x = xs / self.num_kernels
x = F.leaky_relu(x)
x = self.conv_post(x)
x = torch.tanh(x)
return x
def remove_weight_norm(self):
for l in self.ups:
remove_weight_norm(l)
for l in self.resblocks:
l.remove_weight_norm()
class SineGen(torch.nn.Module):
""" Definition of sine generator
SineGen(samp_rate, harmonic_num = 0,
sine_amp = 0.1, noise_std = 0.003,
voiced_threshold = 0,
flag_for_pulse=False)
samp_rate: sampling rate in Hz
harmonic_num: number of harmonic overtones (default 0)
sine_amp: amplitude of sine-wavefrom (default 0.1)
noise_std: std of Gaussian noise (default 0.003)
voiced_thoreshold: F0 threshold for U/V classification (default 0)
flag_for_pulse: this SinGen is used inside PulseGen (default False)
Note: when flag_for_pulse is True, the first time step of a voiced
segment is always sin(np.pi) or cos(0)
"""
def __init__(self, samp_rate, harmonic_num=0,
sine_amp=0.1, noise_std=0.003,
voiced_threshold=0,
flag_for_pulse=False):
super(SineGen, self).__init__()
self.sine_amp = sine_amp
self.noise_std = noise_std
self.harmonic_num = harmonic_num
self.dim = self.harmonic_num + 1
self.sampling_rate = samp_rate
self.voiced_threshold = voiced_threshold
def _f02uv(self, f0):
# generate uv signal
uv = torch.ones_like(f0)
uv = uv * (f0 > self.voiced_threshold)
return uv
def forward(self, f0,upp):
""" sine_tensor, uv = forward(f0)
input F0: tensor(batchsize=1, length, dim=1)
f0 for unvoiced steps should be 0
output sine_tensor: tensor(batchsize=1, length, dim)
output uv: tensor(batchsize=1, length, 1)
"""
with torch.no_grad():
f0 = f0[:, None].transpose(1, 2)
f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim,device=f0.device)
# fundamental component
f0_buf[:, :, 0] = f0[:, :, 0]
for idx in np.arange(self.harmonic_num):f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (idx + 2)# idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic
rad_values = (f0_buf / self.sampling_rate) % 1###%1意味着n_har的乘积无法后处理优化
rand_ini = torch.rand(f0_buf.shape[0], f0_buf.shape[2], device=f0_buf.device)
rand_ini[:, 0] = 0
rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini
tmp_over_one = torch.cumsum(rad_values, 1)# % 1 #####%1意味着后面的cumsum无法再优化
tmp_over_one*=upp
tmp_over_one=F.interpolate(tmp_over_one.transpose(2, 1), scale_factor=upp, mode='linear', align_corners=True).transpose(2, 1)
rad_values=F.interpolate(rad_values.transpose(2, 1), scale_factor=upp, mode='nearest').transpose(2, 1)#######
tmp_over_one%=1
tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0
cumsum_shift = torch.zeros_like(rad_values)
cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0
sine_waves = torch.sin(torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * np.pi)
sine_waves = sine_waves * self.sine_amp
uv = self._f02uv(f0)
uv = F.interpolate(uv.transpose(2, 1), scale_factor=upp, mode='nearest').transpose(2, 1)
noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3
noise = noise_amp * torch.randn_like(sine_waves)
sine_waves = sine_waves * uv + noise
return sine_waves, uv, noise
class SourceModuleHnNSF(torch.nn.Module):
""" SourceModule for hn-nsf
SourceModule(sampling_rate, harmonic_num=0, sine_amp=0.1,
add_noise_std=0.003, voiced_threshod=0)
sampling_rate: sampling_rate in Hz
harmonic_num: number of harmonic above F0 (default: 0)
sine_amp: amplitude of sine source signal (default: 0.1)
add_noise_std: std of additive Gaussian noise (default: 0.003)
note that amplitude of noise in unvoiced is decided
by sine_amp
voiced_threshold: threhold to set U/V given F0 (default: 0)
Sine_source, noise_source = SourceModuleHnNSF(F0_sampled)
F0_sampled (batchsize, length, 1)
Sine_source (batchsize, length, 1)
noise_source (batchsize, length 1)
uv (batchsize, length, 1)
"""
def __init__(self, sampling_rate, harmonic_num=0, sine_amp=0.1,
add_noise_std=0.003, voiced_threshod=0,is_half=True):
super(SourceModuleHnNSF, self).__init__()
self.sine_amp = sine_amp
self.noise_std = add_noise_std
self.is_half=is_half
# to produce sine waveforms
self.l_sin_gen = SineGen(sampling_rate, harmonic_num,
sine_amp, add_noise_std, voiced_threshod)
# to merge source harmonics into a single excitation
self.l_linear = torch.nn.Linear(harmonic_num + 1, 1)
self.l_tanh = torch.nn.Tanh()
def forward(self, x,upp=None):
sine_wavs, uv, _ = self.l_sin_gen(x,upp)
if(self.is_half==True):sine_wavs=sine_wavs.half()
sine_merge = self.l_tanh(self.l_linear(sine_wavs))
return sine_merge,None,None# noise, uv
class GeneratorNSF(torch.nn.Module):
def __init__(
self,
initial_channel,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
gin_channels=0,
sr=40000,
is_half=False
):
super(GeneratorNSF, self).__init__()
self.num_kernels = len(resblock_kernel_sizes)
self.num_upsamples = len(upsample_rates)
self.f0_upsamp = torch.nn.Upsample(scale_factor=np.prod(upsample_rates))
self.m_source = SourceModuleHnNSF(
sampling_rate=sr,
harmonic_num=0,
is_half=is_half
)
self.noise_convs = nn.ModuleList()
self.conv_pre = Conv1d(
initial_channel, upsample_initial_channel, 7, 1, padding=3
)
resblock = modules.ResBlock1 if resblock == "1" else modules.ResBlock2
self.ups = nn.ModuleList()
for i, (u, k) in enumerate(zip(upsample_rates, upsample_kernel_sizes)):
c_cur = upsample_initial_channel // (2 ** (i + 1))
self.ups.append(
weight_norm(
ConvTranspose1d(
upsample_initial_channel // (2**i),
upsample_initial_channel // (2 ** (i + 1)),
k,
u,
padding=(k - u) // 2,
)
)
)
if i + 1 < len(upsample_rates):
stride_f0 = np.prod(upsample_rates[i + 1:])
self.noise_convs.append(Conv1d(
1, c_cur, kernel_size=stride_f0 * 2, stride=stride_f0, padding=stride_f0 // 2))
else:
self.noise_convs.append(Conv1d(1, c_cur, kernel_size=1))
self.resblocks = nn.ModuleList()
for i in range(len(self.ups)):
ch = upsample_initial_channel // (2 ** (i + 1))
for j, (k, d) in enumerate(
zip(resblock_kernel_sizes, resblock_dilation_sizes)
):
self.resblocks.append(resblock(ch, k, d))
self.conv_post = Conv1d(ch, 1, 7, 1, padding=3, bias=False)
self.ups.apply(init_weights)
if gin_channels != 0:
self.cond = nn.Conv1d(gin_channels, upsample_initial_channel, 1)
self.upp=np.prod(upsample_rates)
def forward(self, x, f0,g=None):
har_source, noi_source, uv = self.m_source(f0,self.upp)
har_source = har_source.transpose(1, 2)
x = self.conv_pre(x)
if g is not None:
x = x + self.cond(g)
for i in range(self.num_upsamples):
x = F.leaky_relu(x, modules.LRELU_SLOPE)
x = self.ups[i](x)
x_source = self.noise_convs[i](har_source)
x = x + x_source
xs = None
for j in range(self.num_kernels):
if xs is None:
xs = self.resblocks[i * self.num_kernels + j](x)
else:
xs += self.resblocks[i * self.num_kernels + j](x)
x = xs / self.num_kernels
x = F.leaky_relu(x)
x = self.conv_post(x)
x = torch.tanh(x)
return x
def remove_weight_norm(self):
for l in self.ups:
remove_weight_norm(l)
for l in self.resblocks:
l.remove_weight_norm()
class SynthesizerTrnMs256NSF(nn.Module):
"""
Synthesizer for Training
"""
def __init__(
self,
spec_channels,
segment_size,
inter_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
spk_embed_dim,
gin_channels=0,
sr=40000,
**kwargs
):
super().__init__()
self.spec_channels = spec_channels
self.inter_channels = inter_channels
self.hidden_channels = hidden_channels
self.filter_channels = filter_channels
self.n_heads = n_heads
self.n_layers = n_layers
self.kernel_size = kernel_size
self.p_dropout = p_dropout
self.resblock = resblock
self.resblock_kernel_sizes = resblock_kernel_sizes
self.resblock_dilation_sizes = resblock_dilation_sizes
self.upsample_rates = upsample_rates
self.upsample_initial_channel = upsample_initial_channel
self.upsample_kernel_sizes = upsample_kernel_sizes
self.segment_size = segment_size
self.gin_channels = gin_channels
self.spk_embed_dim=spk_embed_dim
self.enc_p = TextEncoder256(
inter_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
)
self.dec = GeneratorNSF(
inter_channels,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
gin_channels=0,
sr=sr,
is_half=kwargs["is_half"]
)
self.enc_q = PosteriorEncoder(
spec_channels,
inter_channels,
hidden_channels,
5,
1,
16,
gin_channels=gin_channels,
)
self.flow = ResidualCouplingBlock(
inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
)
self.emb_g = nn.Linear(self.spk_embed_dim, gin_channels)
def remove_weight_norm(self):
self.dec.remove_weight_norm()
self.flow.remove_weight_norm()
self.enc_q.remove_weight_norm()
def infer(self, phone, phone_lengths, pitch,pitchf, ds,max_len=None):
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
if("float16"in str(m_p.dtype)):ds=ds.half()
ds=ds.to(m_p.device)
g = self.emb_g(ds).unsqueeze(-1) # [b, h, 1]#
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66) * x_mask
z = self.flow(z_p, x_mask, g=g, reverse=True)
o = self.dec((z * x_mask)[:, :, :max_len],pitchf, g=None)
return o, x_mask, (z, z_p, m_p, logs_p)
class SynthesizerTrn256NSFkm(nn.Module):
"""
Synthesizer for Training
"""
def __init__(
self,
spec_channels,
segment_size,
inter_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
spk_embed_dim,
gin_channels=0,
sr=40000,
**kwargs
):
super().__init__()
self.spec_channels = spec_channels
self.inter_channels = inter_channels
self.hidden_channels = hidden_channels
self.filter_channels = filter_channels
self.n_heads = n_heads
self.n_layers = n_layers
self.kernel_size = kernel_size
self.p_dropout = p_dropout
self.resblock = resblock
self.resblock_kernel_sizes = resblock_kernel_sizes
self.resblock_dilation_sizes = resblock_dilation_sizes
self.upsample_rates = upsample_rates
self.upsample_initial_channel = upsample_initial_channel
self.upsample_kernel_sizes = upsample_kernel_sizes
self.segment_size = segment_size
self.gin_channels = gin_channels
self.enc_p = TextEncoder256km(
inter_channels,
hidden_channels,
filter_channels,
n_heads,
n_layers,
kernel_size,
p_dropout,
)
self.dec = GeneratorNSF(
inter_channels,
resblock,
resblock_kernel_sizes,
resblock_dilation_sizes,
upsample_rates,
upsample_initial_channel,
upsample_kernel_sizes,
gin_channels=0,
sr=sr,
is_half=kwargs["is_half"]
)
self.enc_q = PosteriorEncoder(
spec_channels,
inter_channels,
hidden_channels,
5,
1,
16,
gin_channels=gin_channels,
)
self.flow = ResidualCouplingBlock(
inter_channels, hidden_channels, 5, 1, 3, gin_channels=gin_channels
)
def remove_weight_norm(self):
self.dec.remove_weight_norm()
self.flow.remove_weight_norm()
self.enc_q.remove_weight_norm()
def forward(self, phone, phone_lengths, pitch, pitchf, y, y_lengths):
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
z, m_q, logs_q, y_mask = self.enc_q(y, y_lengths, g=None)
z_p = self.flow(z, y_mask, g=None)
z_slice, ids_slice = commons.rand_slice_segments(
z, y_lengths, self.segment_size
)
pitchf = commons.slice_segments2(
pitchf, ids_slice, self.segment_size
)
o = self.dec(z_slice, pitchf,g=None)
return o, ids_slice, x_mask, y_mask, (z, z_p, m_p, logs_p, m_q, logs_q)
def infer(self, phone, phone_lengths, pitch, nsff0,max_len=None):
# torch.cuda.synchronize()
# t0=ttime()
m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths)
# torch.cuda.synchronize()
# t1=ttime()
z_p = (m_p + torch.exp(logs_p) * torch.randn_like(m_p) * 0.66) * x_mask
# torch.cuda.synchronize()
# t2=ttime()
z = self.flow(z_p, x_mask, g=None, reverse=True)
# torch.cuda.synchronize()
# t3=ttime()
o = self.dec((z * x_mask)[:, :, :max_len], nsff0,g=None)
# torch.cuda.synchronize()
# t4=ttime()
# print(1233333333333333333333333,t1-t0,t2-t1,t3-t2,t4-t3)
return o, x_mask, (z, z_p, m_p, logs_p)