vits/commons.py

import torch
from torch.nn import functional as F
import torch.jit


def script_method(fn, _rcb=None):
  return fn


def script(obj, optimize=True, _frames_up=0, _rcb=None):
  return obj


torch.jit.script_method = script_method
torch.jit.script = script


def init_weights(m, mean=0.0, std=0.01):
  classname = m.__class__.__name__
  if classname.find("Conv") != -1:
    m.weight.data.normal_(mean, std)


def get_padding(kernel_size, dilation=1):
  return int((kernel_size*dilation - dilation)/2)


def intersperse(lst, item):
  result = [item] * (len(lst) * 2 + 1)
  result[1::2] = lst
  return result


def slice_segments(x, ids_str, segment_size=4):
  ret = torch.zeros_like(x[:, :, :segment_size])
  for i in range(x.size(0)):
    idx_str = ids_str[i]
    idx_end = idx_str + segment_size
    ret[i] = x[i, :, idx_str:idx_end]
  return ret


def rand_slice_segments(x, x_lengths=None, segment_size=4):
  b, d, t = x.size()
  if x_lengths is None:
    x_lengths = t
  ids_str_max = x_lengths - segment_size + 1
  ids_str = (torch.rand([b]).to(device=x.device) * ids_str_max).to(dtype=torch.long)
  ret = slice_segments(x, ids_str, segment_size)
  return ret, ids_str


def subsequent_mask(length):
  mask = torch.tril(torch.ones(length, length)).unsqueeze(0).unsqueeze(0)
  return mask


@torch.jit.script
def fused_add_tanh_sigmoid_multiply(input_a, input_b, n_channels):
  n_channels_int = n_channels[0]
  in_act = input_a + input_b
  t_act = torch.tanh(in_act[:, :n_channels_int, :])
  s_act = torch.sigmoid(in_act[:, n_channels_int:, :])
  acts = t_act * s_act
  return acts


def convert_pad_shape(pad_shape):
  l = pad_shape[::-1]
  pad_shape = [item for sublist in l for item in sublist]
  return pad_shape


def sequence_mask(length, max_length=None):
  if max_length is None:
    max_length = length.max()
  x = torch.arange(max_length, dtype=length.dtype, device=length.device)
  return x.unsqueeze(0) < length.unsqueeze(1)


def generate_path(duration, mask):
  """
  duration: [b, 1, t_x]
  mask: [b, 1, t_y, t_x]
  """
  device = duration.device
  
  b, _, t_y, t_x = mask.shape
  cum_duration = torch.cumsum(duration, -1)
  
  cum_duration_flat = cum_duration.view(b * t_x)
  path = sequence_mask(cum_duration_flat, t_y).to(mask.dtype)
  path = path.view(b, t_x, t_y)
  path = path - F.pad(path, convert_pad_shape([[0, 0], [1, 0], [0, 0]]))[:, :-1]
  path = path.unsqueeze(1).transpose(2,3) * mask
  return path