Medix-AI/coqui-tts
Medix-AI
/
coqui-tts
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Corrected Code Style

This commit is contained in:
Matthew Boakes 2023-11-08 20:05:55 +00:00
parent d0f34b2fd9
commit 2deccb6eb3
7 changed files with 17 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
TTS/tts/layers/delightful_tts/conv_layers.py
View File

@ -3,7 +3,7 @@ from typing import Tuple
import torch
import torch.nn as nn # pylint: disable=consider-using-from-import
import torch.nn.functional as F
import torch.nn.utils.parametrize as parametrize
from torch.nn.utils import parametrize
from TTS.tts.layers.delightful_tts.kernel_predictor import KernelPredictor

6
TTS/tts/layers/delightful_tts/kernel_predictor.py
View File

@ -1,5 +1,5 @@
import torch.nn as nn # pylint: disable=consider-using-from-import
import torch.nn.utils.parametrize as parametrize
from torch.nn.utils import parametrize
class KernelPredictor(nn.Module):
@ -37,7 +37,9 @@ class KernelPredictor(nn.Module):
kpnet_bias_channels = conv_out_channels * conv_layers # l_b
self.input_conv = nn.Sequential(
nn.utils.parametrizations.weight_norm(nn.Conv1d(cond_channels, kpnet_hidden_channels, 5, padding=2, bias=True)),
nn.utils.parametrizations.weight_norm(
nn.Conv1d(cond_channels, kpnet_hidden_channels, 5, padding=2, bias=True)
),
getattr(nn, kpnet_nonlinear_activation)(**kpnet_nonlinear_activation_params),
)

2
TTS/tts/layers/generic/wavenet.py
View File

@ -1,6 +1,6 @@
import torch
import torch.nn.utils.parametrize as parametrize
from torch import nn
from torch.nn.utils import parametrize
@torch.jit.script

8
TTS/tts/layers/tortoise/vocoder.py
View File

@ -44,7 +44,9 @@ class KernelPredictor(torch.nn.Module):
kpnet_bias_channels = conv_out_channels * conv_layers # l_b
self.input_conv = nn.Sequential(
nn.utils.parametrizations.weight_norm(nn.Conv1d(cond_channels, kpnet_hidden_channels, 5, padding=2, bias=True)),
nn.utils.parametrizations.weight_norm(
nn.Conv1d(cond_channels, kpnet_hidden_channels, 5, padding=2, bias=True)
),
getattr(nn, kpnet_nonlinear_activation)(**kpnet_nonlinear_activation_params),
)
@ -314,7 +316,9 @@ class UnivNetGenerator(nn.Module):
)
)
self.conv_pre = nn.utils.parametrizations.weight_norm(nn.Conv1d(noise_dim, channel_size, 7, padding=3, padding_mode="reflect"))
self.conv_pre = nn.utils.parametrizations.weight_norm(
nn.Conv1d(noise_dim, channel_size, 7, padding=3, padding_mode="reflect")
)
self.conv_post = nn.Sequential(
nn.LeakyReLU(lReLU_slope),

4
TTS/vocoder/layers/hifigan.py
View File

@ -11,7 +11,9 @@ class ResStack(nn.Module):
resstack += [
nn.LeakyReLU(0.2),
nn.ReflectionPad1d(dilation),
nn.utils.parametrizations.weight_norm(nn.Conv1d(channel, channel, kernel_size=kernel, dilation=dilation)),
nn.utils.parametrizations.weight_norm(
nn.Conv1d(channel, channel, kernel_size=kernel, dilation=dilation)
),
nn.LeakyReLU(0.2),
nn.ReflectionPad1d(padding),
nn.utils.parametrizations.weight_norm(nn.Conv1d(channel, channel, kernel_size=1)),

2
TTS/vocoder/models/univnet_generator.py
View File

@ -3,7 +3,7 @@ from typing import List
import numpy as np
import torch
import torch.nn.functional as F
import torch.nn.utils.parametrize as parametrize
from torch.nn.utils import parametrize
from TTS.vocoder.layers.lvc_block import LVCBlock

2
TTS/vocoder/models/wavegrad.py
View File

@ -6,10 +6,10 @@ import torch
from coqpit import Coqpit
from torch import nn
from torch.nn.utils.parametrizations import weight_norm
from torch.nn.utils.parametrize import remove_parametrizations
from torch.utils.data import DataLoader
from torch.utils.data.distributed import DistributedSampler
from trainer.trainer_utils import get_optimizer, get_scheduler
from torch.nn.utils.parametrize import remove_parametrizations
from TTS.utils.io import load_fsspec
from TTS.vocoder.datasets import WaveGradDataset