mirror of
https://github.com/babysor/Realtime-Voice-Clone-Chinese.git
synced 2026-02-03 18:43:41 +08:00
Compare commits
2 Commits
Add-GST
...
webtoolbox
| Author | SHA1 | Date | |
|---|---|---|---|
|
3713d64cc7 | ||
|
|
5e7cc82373 |
4
.gitignore
vendored
4
.gitignore
vendored
@@ -17,7 +17,5 @@
|
||||
*.sh
|
||||
synthesizer/saved_models/*
|
||||
vocoder/saved_models/*
|
||||
encoder/saved_models/*
|
||||
cp_hifigan/*
|
||||
!vocoder/saved_models/pretrained/*
|
||||
!encoder/saved_models/pretrained.pt
|
||||
!vocoder/saved_models/pretrained/*
|
||||
18
.vscode/launch.json
vendored
18
.vscode/launch.json
vendored
@@ -17,7 +17,7 @@
|
||||
"request": "launch",
|
||||
"program": "vocoder_preprocess.py",
|
||||
"console": "integratedTerminal",
|
||||
"args": ["..\\audiodata"]
|
||||
"args": ["..\\..\\chs1"]
|
||||
},
|
||||
{
|
||||
"name": "Python: Vocoder Train",
|
||||
@@ -25,23 +25,15 @@
|
||||
"request": "launch",
|
||||
"program": "vocoder_train.py",
|
||||
"console": "integratedTerminal",
|
||||
"args": ["dev", "..\\audiodata"]
|
||||
"args": ["dev", "..\\..\\chs1"]
|
||||
},
|
||||
{
|
||||
"name": "Python: Demo Box",
|
||||
"name": "Python: demo box",
|
||||
"type": "python",
|
||||
"request": "launch",
|
||||
"program": "demo_toolbox.py",
|
||||
"console": "integratedTerminal",
|
||||
"args": ["-d","..\\audiodata"]
|
||||
},
|
||||
{
|
||||
"name": "Python: Synth Train",
|
||||
"type": "python",
|
||||
"request": "launch",
|
||||
"program": "synthesizer_train.py",
|
||||
"console": "integratedTerminal",
|
||||
"args": ["my_run", "..\\"]
|
||||
},
|
||||
"args": ["-d", "..\\..\\chs"]
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
11
README-CN.md
11
README-CN.md
@@ -5,7 +5,7 @@
|
||||
|
||||
### [English](README.md) | 中文
|
||||
|
||||
### [DEMO VIDEO](https://www.bilibili.com/video/BV17Q4y1B7mY/)
|
||||
### [DEMO VIDEO](https://www.bilibili.com/video/BV1sA411P7wM/)
|
||||
|
||||
## 特性
|
||||
🌍 **中文** 支持普通话并使用多种中文数据集进行测试：aidatatang_200zh, magicdata, aishell3， biaobei，MozillaCommonVoice 等
|
||||
@@ -119,20 +119,15 @@
|
||||
|
||||
| URL | Designation | 标题 | 实现源码 |
|
||||
| --- | ----------- | ----- | --------------------- |
|
||||
| [1803.09017](https://arxiv.org/abs/1803.09017) | GlobalStyleToken (synthesizer)| Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis | 本代码库 |
|
||||
| [2010.05646](https://arxiv.org/abs/2010.05646) | HiFi-GAN (vocoder)| Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis | 本代码库 |
|
||||
|[**1806.04558**](https://arxiv.org/pdf/1806.04558.pdf) | SV2TTS | Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis | This repo |
|
||||
|[**1806.04558**](https://arxiv.org/pdf/1806.04558.pdf) | **SV2TTS** | **Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis** | This repo |
|
||||
|[1802.08435](https://arxiv.org/pdf/1802.08435.pdf) | WaveRNN (vocoder) | Efficient Neural Audio Synthesis | [fatchord/WaveRNN](https://github.com/fatchord/WaveRNN) |
|
||||
|[1703.10135](https://arxiv.org/pdf/1703.10135.pdf) | Tacotron (synthesizer) | Tacotron: Towards End-to-End Speech Synthesis | [fatchord/WaveRNN](https://github.com/fatchord/WaveRNN)
|
||||
|[1710.10467](https://arxiv.org/pdf/1710.10467.pdf) | GE2E (encoder)| Generalized End-To-End Loss for Speaker Verification | 本代码库 |
|
||||
|
||||
## 常見問題(FQ&A)
|
||||
#### 1.數據集哪裡下載?
|
||||
| 数据集 | OpenSLR地址 | 其他源 (Google Drive, Baidu网盘等) |
|
||||
| --- | ----------- | ---------------|
|
||||
| aidatatang_200zh | [OpenSLR](http://www.openslr.org/62/) | [Google Drive](https://drive.google.com/file/d/110A11KZoVe7vy6kXlLb6zVPLb_J91I_t/view?usp=sharing) |
|
||||
| magicdata | [OpenSLR](http://www.openslr.org/68/) | [Google Drive (Dev set)](https://drive.google.com/file/d/1g5bWRUSNH68ycC6eNvtwh07nX3QhOOlo/view?usp=sharing) |
|
||||
| aishell3 | [OpenSLR](https://www.openslr.org/93/) | [Google Drive](https://drive.google.com/file/d/1shYp_o4Z0X0cZSKQDtFirct2luFUwKzZ/view?usp=sharing) |
|
||||
[aidatatang_200zh](http://www.openslr.org/62/)、[magicdata](http://www.openslr.org/68/)、[aishell3](http://www.openslr.org/93/)
|
||||
> 解壓 aidatatang_200zh 後，還需將 `aidatatang_200zh\corpus\train`下的檔案全選解壓縮
|
||||
|
||||
#### 2.`<datasets_root>`是什麼意思?
|
||||
|
||||
@@ -16,7 +16,7 @@
|
||||
|
||||
🌍 **Webserver Ready** to serve your result with remote calling
|
||||
|
||||
### [DEMO VIDEO](https://www.bilibili.com/video/BV17Q4y1B7mY/)
|
||||
### [DEMO VIDEO](https://www.bilibili.com/video/BV1sA411P7wM/)
|
||||
|
||||
## Quick Start
|
||||
|
||||
@@ -77,7 +77,6 @@ You can then try the toolbox:
|
||||
|
||||
| URL | Designation | Title | Implementation source |
|
||||
| --- | ----------- | ----- | --------------------- |
|
||||
| [1803.09017](https://arxiv.org/abs/1803.09017) | GlobalStyleToken (synthesizer)| Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis | This repo |
|
||||
| [2010.05646](https://arxiv.org/abs/2010.05646) | HiFi-GAN (vocoder)| Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis | This repo |
|
||||
|[**1806.04558**](https://arxiv.org/pdf/1806.04558.pdf) | **SV2TTS** | **Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis** | This repo |
|
||||
|[1802.08435](https://arxiv.org/pdf/1802.08435.pdf) | WaveRNN (vocoder) | Efficient Neural Audio Synthesis | [fatchord/WaveRNN](https://github.com/fatchord/WaveRNN) |
|
||||
@@ -86,11 +85,7 @@ You can then try the toolbox:
|
||||
|
||||
## F Q&A
|
||||
#### 1.Where can I download the dataset?
|
||||
| Dataset | Original Source | Alternative Sources |
|
||||
| --- | ----------- | ---------------|
|
||||
| aidatatang_200zh | [OpenSLR](http://www.openslr.org/62/) | [Google Drive](https://drive.google.com/file/d/110A11KZoVe7vy6kXlLb6zVPLb_J91I_t/view?usp=sharing) |
|
||||
| magicdata | [OpenSLR](http://www.openslr.org/68/) | [Google Drive (Dev set)](https://drive.google.com/file/d/1g5bWRUSNH68ycC6eNvtwh07nX3QhOOlo/view?usp=sharing) |
|
||||
| aishell3 | [OpenSLR](https://www.openslr.org/93/) | [Google Drive](https://drive.google.com/file/d/1shYp_o4Z0X0cZSKQDtFirct2luFUwKzZ/view?usp=sharing) |
|
||||
[aidatatang_200zh](http://www.openslr.org/62/)、[magicdata](http://www.openslr.org/68/)、[aishell3](http://www.openslr.org/93/)
|
||||
> After unzip aidatatang_200zh, you need to unzip all the files under `aidatatang_200zh\corpus\train`
|
||||
|
||||
#### 2.What is`<datasets_root>`?
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from encoder.preprocess import preprocess_librispeech, preprocess_voxceleb1, preprocess_voxceleb2, preprocess_aidatatang_200zh
|
||||
from encoder.preprocess import preprocess_librispeech, preprocess_voxceleb1, preprocess_voxceleb2
|
||||
from utils.argutils import print_args
|
||||
from pathlib import Path
|
||||
import argparse
|
||||
@@ -10,7 +10,17 @@ if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Preprocesses audio files from datasets, encodes them as mel spectrograms and "
|
||||
"writes them to the disk. This will allow you to train the encoder. The "
|
||||
"datasets required are at least one of LibriSpeech, VoxCeleb1, VoxCeleb2, aidatatang_200zh. ",
|
||||
"datasets required are at least one of VoxCeleb1, VoxCeleb2 and LibriSpeech. "
|
||||
"Ideally, you should have all three. You should extract them as they are "
|
||||
"after having downloaded them and put them in a same directory, e.g.:\n"
|
||||
"-[datasets_root]\n"
|
||||
" -LibriSpeech\n"
|
||||
" -train-other-500\n"
|
||||
" -VoxCeleb1\n"
|
||||
" -wav\n"
|
||||
" -vox1_meta.csv\n"
|
||||
" -VoxCeleb2\n"
|
||||
" -dev",
|
||||
formatter_class=MyFormatter
|
||||
)
|
||||
parser.add_argument("datasets_root", type=Path, help=\
|
||||
@@ -19,7 +29,7 @@ if __name__ == "__main__":
|
||||
"Path to the output directory that will contain the mel spectrograms. If left out, "
|
||||
"defaults to <datasets_root>/SV2TTS/encoder/")
|
||||
parser.add_argument("-d", "--datasets", type=str,
|
||||
default="librispeech_other,voxceleb1,aidatatang_200zh", help=\
|
||||
default="librispeech_other,voxceleb1,voxceleb2", help=\
|
||||
"Comma-separated list of the name of the datasets you want to preprocess. Only the train "
|
||||
"set of these datasets will be used. Possible names: librispeech_other, voxceleb1, "
|
||||
"voxceleb2.")
|
||||
@@ -53,7 +63,6 @@ if __name__ == "__main__":
|
||||
"librispeech_other": preprocess_librispeech,
|
||||
"voxceleb1": preprocess_voxceleb1,
|
||||
"voxceleb2": preprocess_voxceleb2,
|
||||
"aidatatang_200zh": preprocess_aidatatang_200zh,
|
||||
}
|
||||
args = vars(args)
|
||||
for dataset in args.pop("datasets"):
|
||||
@@ -117,15 +117,6 @@ def _preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir,
|
||||
logger.finalize()
|
||||
print("Done preprocessing %s.\n" % dataset_name)
|
||||
|
||||
def preprocess_aidatatang_200zh(datasets_root: Path, out_dir: Path, skip_existing=False):
|
||||
dataset_name = "aidatatang_200zh"
|
||||
dataset_root, logger = _init_preprocess_dataset(dataset_name, datasets_root, out_dir)
|
||||
if not dataset_root:
|
||||
return
|
||||
# Preprocess all speakers
|
||||
speaker_dirs = list(dataset_root.joinpath("corpus", "train").glob("*"))
|
||||
_preprocess_speaker_dirs(speaker_dirs, dataset_name, datasets_root, out_dir, "wav",
|
||||
skip_existing, logger)
|
||||
|
||||
def preprocess_librispeech(datasets_root: Path, out_dir: Path, skip_existing=False):
|
||||
for dataset_name in librispeech_datasets["train"]["other"]:
|
||||
|
||||
Binary file not shown.
@@ -19,5 +19,4 @@ flask
|
||||
flask_wtf
|
||||
flask_cors
|
||||
gevent==21.8.0
|
||||
flask_restx
|
||||
tensorboard
|
||||
flask_restx
|
||||
@@ -1,13 +0,0 @@
|
||||
class GSTHyperparameters():
|
||||
E = 512
|
||||
|
||||
# reference encoder
|
||||
ref_enc_filters = [32, 32, 64, 64, 128, 128]
|
||||
|
||||
# style token layer
|
||||
token_num = 10
|
||||
# token_emb_size = 256
|
||||
num_heads = 8
|
||||
|
||||
n_mels = 256 # Number of Mel banks to generate
|
||||
|
||||
@@ -49,15 +49,12 @@ hparams = HParams(
|
||||
# frame that has all values < -3.4
|
||||
|
||||
### Tacotron Training
|
||||
tts_schedule = [(2, 1e-3, 10_000, 12), # Progressive training schedule
|
||||
(2, 5e-4, 15_000, 12), # (r, lr, step, batch_size)
|
||||
(2, 2e-4, 20_000, 12), # (r, lr, step, batch_size)
|
||||
(2, 1e-4, 30_000, 12), #
|
||||
(2, 5e-5, 40_000, 12), #
|
||||
(2, 1e-5, 60_000, 12), #
|
||||
(2, 5e-6, 160_000, 12), # r = reduction factor (# of mel frames
|
||||
(2, 3e-6, 320_000, 12), # synthesized for each decoder iteration)
|
||||
(2, 1e-6, 640_000, 12)], # lr = learning rate
|
||||
tts_schedule = [(2, 1e-3, 20_000, 24), # Progressive training schedule
|
||||
(2, 5e-4, 40_000, 24), # (r, lr, step, batch_size)
|
||||
(2, 2e-4, 80_000, 24), #
|
||||
(2, 1e-4, 160_000, 24), # r = reduction factor (# of mel frames
|
||||
(2, 3e-5, 320_000, 24), # synthesized for each decoder iteration)
|
||||
(2, 1e-5, 640_000, 24)], # lr = learning rate
|
||||
|
||||
tts_clip_grad_norm = 1.0, # clips the gradient norm to prevent explosion - set to None if not needed
|
||||
tts_eval_interval = 500, # Number of steps between model evaluation (sample generation)
|
||||
|
||||
@@ -70,7 +70,7 @@ class Synthesizer:
|
||||
|
||||
def synthesize_spectrograms(self, texts: List[str],
|
||||
embeddings: Union[np.ndarray, List[np.ndarray]],
|
||||
return_alignments=False, style_idx=0):
|
||||
return_alignments=False):
|
||||
"""
|
||||
Synthesizes mel spectrograms from texts and speaker embeddings.
|
||||
|
||||
@@ -125,7 +125,7 @@ class Synthesizer:
|
||||
speaker_embeddings = torch.tensor(speaker_embeds).float().to(self.device)
|
||||
|
||||
# Inference
|
||||
_, mels, alignments = self._model.generate(chars, speaker_embeddings, style_idx=style_idx)
|
||||
_, mels, alignments = self._model.generate(chars, speaker_embeddings)
|
||||
mels = mels.detach().cpu().numpy()
|
||||
for m in mels:
|
||||
# Trim silence from end of each spectrogram
|
||||
|
||||
@@ -1,135 +0,0 @@
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.init as init
|
||||
import torch.nn.functional as tFunctional
|
||||
from synthesizer.gst_hyperparameters import GSTHyperparameters as hp
|
||||
|
||||
|
||||
class GlobalStyleToken(nn.Module):
|
||||
|
||||
def __init__(self):
|
||||
|
||||
super().__init__()
|
||||
self.encoder = ReferenceEncoder()
|
||||
self.stl = STL()
|
||||
|
||||
def forward(self, inputs):
|
||||
enc_out = self.encoder(inputs)
|
||||
style_embed = self.stl(enc_out)
|
||||
|
||||
return style_embed
|
||||
|
||||
|
||||
class ReferenceEncoder(nn.Module):
|
||||
'''
|
||||
inputs --- [N, Ty/r, n_mels*r] mels
|
||||
outputs --- [N, ref_enc_gru_size]
|
||||
'''
|
||||
|
||||
def __init__(self):
|
||||
|
||||
super().__init__()
|
||||
K = len(hp.ref_enc_filters)
|
||||
filters = [1] + hp.ref_enc_filters
|
||||
convs = [nn.Conv2d(in_channels=filters[i],
|
||||
out_channels=filters[i + 1],
|
||||
kernel_size=(3, 3),
|
||||
stride=(2, 2),
|
||||
padding=(1, 1)) for i in range(K)]
|
||||
self.convs = nn.ModuleList(convs)
|
||||
self.bns = nn.ModuleList([nn.BatchNorm2d(num_features=hp.ref_enc_filters[i]) for i in range(K)])
|
||||
|
||||
out_channels = self.calculate_channels(hp.n_mels, 3, 2, 1, K)
|
||||
self.gru = nn.GRU(input_size=hp.ref_enc_filters[-1] * out_channels,
|
||||
hidden_size=hp.E // 2,
|
||||
batch_first=True)
|
||||
|
||||
def forward(self, inputs):
|
||||
N = inputs.size(0)
|
||||
out = inputs.view(N, 1, -1, hp.n_mels) # [N, 1, Ty, n_mels]
|
||||
for conv, bn in zip(self.convs, self.bns):
|
||||
out = conv(out)
|
||||
out = bn(out)
|
||||
out = tFunctional.relu(out) # [N, 128, Ty//2^K, n_mels//2^K]
|
||||
|
||||
out = out.transpose(1, 2) # [N, Ty//2^K, 128, n_mels//2^K]
|
||||
T = out.size(1)
|
||||
N = out.size(0)
|
||||
out = out.contiguous().view(N, T, -1) # [N, Ty//2^K, 128*n_mels//2^K]
|
||||
|
||||
self.gru.flatten_parameters()
|
||||
memory, out = self.gru(out) # out --- [1, N, E//2]
|
||||
|
||||
return out.squeeze(0)
|
||||
|
||||
def calculate_channels(self, L, kernel_size, stride, pad, n_convs):
|
||||
for i in range(n_convs):
|
||||
L = (L - kernel_size + 2 * pad) // stride + 1
|
||||
return L
|
||||
|
||||
|
||||
class STL(nn.Module):
|
||||
'''
|
||||
inputs --- [N, E//2]
|
||||
'''
|
||||
|
||||
def __init__(self):
|
||||
|
||||
super().__init__()
|
||||
self.embed = nn.Parameter(torch.FloatTensor(hp.token_num, hp.E // hp.num_heads))
|
||||
d_q = hp.E // 2
|
||||
d_k = hp.E // hp.num_heads
|
||||
# self.attention = MultiHeadAttention(hp.num_heads, d_model, d_q, d_v)
|
||||
self.attention = MultiHeadAttention(query_dim=d_q, key_dim=d_k, num_units=hp.E, num_heads=hp.num_heads)
|
||||
|
||||
init.normal_(self.embed, mean=0, std=0.5)
|
||||
|
||||
def forward(self, inputs):
|
||||
N = inputs.size(0)
|
||||
query = inputs.unsqueeze(1) # [N, 1, E//2]
|
||||
keys = tFunctional.tanh(self.embed).unsqueeze(0).expand(N, -1, -1) # [N, token_num, E // num_heads]
|
||||
style_embed = self.attention(query, keys)
|
||||
|
||||
return style_embed
|
||||
|
||||
|
||||
class MultiHeadAttention(nn.Module):
|
||||
'''
|
||||
input:
|
||||
query --- [N, T_q, query_dim]
|
||||
key --- [N, T_k, key_dim]
|
||||
output:
|
||||
out --- [N, T_q, num_units]
|
||||
'''
|
||||
|
||||
def __init__(self, query_dim, key_dim, num_units, num_heads):
|
||||
|
||||
super().__init__()
|
||||
self.num_units = num_units
|
||||
self.num_heads = num_heads
|
||||
self.key_dim = key_dim
|
||||
|
||||
self.W_query = nn.Linear(in_features=query_dim, out_features=num_units, bias=False)
|
||||
self.W_key = nn.Linear(in_features=key_dim, out_features=num_units, bias=False)
|
||||
self.W_value = nn.Linear(in_features=key_dim, out_features=num_units, bias=False)
|
||||
|
||||
def forward(self, query, key):
|
||||
querys = self.W_query(query) # [N, T_q, num_units]
|
||||
keys = self.W_key(key) # [N, T_k, num_units]
|
||||
values = self.W_value(key)
|
||||
|
||||
split_size = self.num_units // self.num_heads
|
||||
querys = torch.stack(torch.split(querys, split_size, dim=2), dim=0) # [h, N, T_q, num_units/h]
|
||||
keys = torch.stack(torch.split(keys, split_size, dim=2), dim=0) # [h, N, T_k, num_units/h]
|
||||
values = torch.stack(torch.split(values, split_size, dim=2), dim=0) # [h, N, T_k, num_units/h]
|
||||
|
||||
# score = softmax(QK^T / (d_k ** 0.5))
|
||||
scores = torch.matmul(querys, keys.transpose(2, 3)) # [h, N, T_q, T_k]
|
||||
scores = scores / (self.key_dim ** 0.5)
|
||||
scores = tFunctional.softmax(scores, dim=3)
|
||||
|
||||
# out = score * V
|
||||
out = torch.matmul(scores, values) # [h, N, T_q, num_units/h]
|
||||
out = torch.cat(torch.split(out, 1, dim=0), dim=3).squeeze(0) # [N, T_q, num_units]
|
||||
|
||||
return out
|
||||
@@ -3,7 +3,8 @@ import numpy as np
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
from synthesizer.models.global_style_token import GlobalStyleToken
|
||||
from pathlib import Path
|
||||
from typing import Union
|
||||
|
||||
|
||||
class HighwayNetwork(nn.Module):
|
||||
@@ -337,7 +338,6 @@ class Tacotron(nn.Module):
|
||||
self.encoder = Encoder(embed_dims, num_chars, encoder_dims,
|
||||
encoder_K, num_highways, dropout)
|
||||
self.encoder_proj = nn.Linear(encoder_dims + speaker_embedding_size, decoder_dims, bias=False)
|
||||
self.gst = GlobalStyleToken()
|
||||
self.decoder = Decoder(n_mels, encoder_dims, decoder_dims, lstm_dims,
|
||||
dropout, speaker_embedding_size)
|
||||
self.postnet = CBHG(postnet_K, n_mels, postnet_dims,
|
||||
@@ -358,11 +358,11 @@ class Tacotron(nn.Module):
|
||||
def r(self, value):
|
||||
self.decoder.r = self.decoder.r.new_tensor(value, requires_grad=False)
|
||||
|
||||
def forward(self, texts, mels, speaker_embedding):
|
||||
def forward(self, x, m, speaker_embedding):
|
||||
device = next(self.parameters()).device # use same device as parameters
|
||||
|
||||
self.step += 1
|
||||
batch_size, _, steps = mels.size()
|
||||
batch_size, _, steps = m.size()
|
||||
|
||||
# Initialise all hidden states and pack into tuple
|
||||
attn_hidden = torch.zeros(batch_size, self.decoder_dims, device=device)
|
||||
@@ -383,12 +383,7 @@ class Tacotron(nn.Module):
|
||||
|
||||
# SV2TTS: Run the encoder with the speaker embedding
|
||||
# The projection avoids unnecessary matmuls in the decoder loop
|
||||
encoder_seq = self.encoder(texts, speaker_embedding)
|
||||
# put after encoder
|
||||
if self.gst is not None:
|
||||
style_embed = self.gst(speaker_embedding)
|
||||
style_embed = style_embed.expand_as(encoder_seq)
|
||||
encoder_seq = encoder_seq + style_embed
|
||||
encoder_seq = self.encoder(x, speaker_embedding)
|
||||
encoder_seq_proj = self.encoder_proj(encoder_seq)
|
||||
|
||||
# Need a couple of lists for outputs
|
||||
@@ -396,10 +391,10 @@ class Tacotron(nn.Module):
|
||||
|
||||
# Run the decoder loop
|
||||
for t in range(0, steps, self.r):
|
||||
prenet_in = mels[:, :, t - 1] if t > 0 else go_frame
|
||||
prenet_in = m[:, :, t - 1] if t > 0 else go_frame
|
||||
mel_frames, scores, hidden_states, cell_states, context_vec, stop_tokens = \
|
||||
self.decoder(encoder_seq, encoder_seq_proj, prenet_in,
|
||||
hidden_states, cell_states, context_vec, t, texts)
|
||||
hidden_states, cell_states, context_vec, t, x)
|
||||
mel_outputs.append(mel_frames)
|
||||
attn_scores.append(scores)
|
||||
stop_outputs.extend([stop_tokens] * self.r)
|
||||
@@ -419,7 +414,7 @@ class Tacotron(nn.Module):
|
||||
|
||||
return mel_outputs, linear, attn_scores, stop_outputs
|
||||
|
||||
def generate(self, x, speaker_embedding=None, steps=200, style_idx=0):
|
||||
def generate(self, x, speaker_embedding=None, steps=2000):
|
||||
self.eval()
|
||||
device = next(self.parameters()).device # use same device as parameters
|
||||
|
||||
@@ -445,18 +440,6 @@ class Tacotron(nn.Module):
|
||||
# SV2TTS: Run the encoder with the speaker embedding
|
||||
# The projection avoids unnecessary matmuls in the decoder loop
|
||||
encoder_seq = self.encoder(x, speaker_embedding)
|
||||
|
||||
# put after encoder
|
||||
if self.gst is not None and style_idx >= 0 and style_idx < 10:
|
||||
gst_embed = self.gst.stl.embed.cpu().data.numpy() #[0, number_token]
|
||||
gst_embed = np.tile(gst_embed, (1, 8))
|
||||
scale = np.zeros(512)
|
||||
scale[:] = 0.3
|
||||
speaker_embedding = (gst_embed[style_idx] * scale).astype(np.float32)
|
||||
speaker_embedding = torch.from_numpy(np.tile(speaker_embedding, (x.shape[0], 1))).to(device)
|
||||
style_embed = self.gst(speaker_embedding)
|
||||
style_embed = style_embed.expand_as(encoder_seq)
|
||||
encoder_seq = encoder_seq + style_embed
|
||||
encoder_seq_proj = self.encoder_proj(encoder_seq)
|
||||
|
||||
# Need a couple of lists for outputs
|
||||
@@ -511,7 +494,7 @@ class Tacotron(nn.Module):
|
||||
# Use device of model params as location for loaded state
|
||||
device = next(self.parameters()).device
|
||||
checkpoint = torch.load(str(path), map_location=device)
|
||||
self.load_state_dict(checkpoint["model_state"], strict=False)
|
||||
self.load_state_dict(checkpoint["model_state"])
|
||||
|
||||
if "optimizer_state" in checkpoint and optimizer is not None:
|
||||
optimizer.load_state_dict(checkpoint["optimizer_state"])
|
||||
|
||||
@@ -71,7 +71,6 @@ class Toolbox:
|
||||
|
||||
# Initialize the events and the interface
|
||||
self.ui = UI()
|
||||
self.style_idx = 0
|
||||
self.reset_ui(enc_models_dir, syn_models_dir, voc_models_dir, seed)
|
||||
self.setup_events()
|
||||
self.ui.start()
|
||||
@@ -234,7 +233,7 @@ class Toolbox:
|
||||
texts = processed_texts
|
||||
embed = self.ui.selected_utterance.embed
|
||||
embeds = [embed] * len(texts)
|
||||
specs = self.synthesizer.synthesize_spectrograms(texts, embeds, style_idx=int(self.ui.style_idx_textbox.text()))
|
||||
specs = self.synthesizer.synthesize_spectrograms(texts, embeds)
|
||||
breaks = [spec.shape[1] for spec in specs]
|
||||
spec = np.concatenate(specs, axis=1)
|
||||
|
||||
|
||||
@@ -574,14 +574,10 @@ class UI(QDialog):
|
||||
self.seed_textbox = QLineEdit()
|
||||
self.seed_textbox.setMaximumWidth(80)
|
||||
layout_seed.addWidget(self.seed_textbox, 0, 1)
|
||||
layout_seed.addWidget(QLabel("Style#:(0~9)"), 0, 2)
|
||||
self.style_idx_textbox = QLineEdit("-1")
|
||||
self.style_idx_textbox.setMaximumWidth(80)
|
||||
layout_seed.addWidget(self.style_idx_textbox, 0, 3)
|
||||
self.trim_silences_checkbox = QCheckBox("Enhance vocoder output")
|
||||
self.trim_silences_checkbox.setToolTip("When checked, trims excess silence in vocoder output."
|
||||
" This feature requires `webrtcvad` to be installed.")
|
||||
layout_seed.addWidget(self.trim_silences_checkbox, 0, 4, 1, 2)
|
||||
layout_seed.addWidget(self.trim_silences_checkbox, 0, 2, 1, 2)
|
||||
gen_layout.addLayout(layout_seed)
|
||||
|
||||
self.loading_bar = QProgressBar()
|
||||
|
||||
@@ -11,6 +11,7 @@ def check_model_paths(encoder_path: Path, synthesizer_path: Path, vocoder_path:
|
||||
|
||||
# If none of the paths exist, remind the user to download models if needed
|
||||
print("********************************************************************************")
|
||||
print("Error: Model files not found. Please download the models")
|
||||
print("Error: Model files not found. Follow these instructions to get and install the models:")
|
||||
print("https://github.com/CorentinJ/Real-Time-Voice-Cloning/wiki/Pretrained-models")
|
||||
print("********************************************************************************\n")
|
||||
quit(-1)
|
||||
|
||||
@@ -9,7 +9,6 @@ from vocoder.wavernn import inference as rnn_vocoder
|
||||
import numpy as np
|
||||
import re
|
||||
from scipy.io.wavfile import write
|
||||
import librosa
|
||||
import io
|
||||
import base64
|
||||
from flask_cors import CORS
|
||||
@@ -31,7 +30,6 @@ def webApp():
|
||||
synthesizers = list(Path(syn_models_dirt).glob("**/*.pt"))
|
||||
synthesizers_cache = {}
|
||||
encoder.load_model(Path("encoder/saved_models/pretrained.pt"))
|
||||
# rnn_vocoder.load_model(Path("vocoder/saved_models/pretrained/pretrained.pt"))
|
||||
gan_vocoder.load_model(Path("vocoder/saved_models/pretrained/g_hifigan.pt"))
|
||||
|
||||
def pcm2float(sig, dtype='float32'):
|
||||
@@ -68,6 +66,7 @@ def webApp():
|
||||
@app.route("/api/synthesize", methods=["POST"])
|
||||
def synthesize():
|
||||
# TODO Implementation with json to support more platform
|
||||
|
||||
# Load synthesizer
|
||||
if "synt_path" in request.form:
|
||||
synt_path = request.form["synt_path"]
|
||||
@@ -81,16 +80,10 @@ def webApp():
|
||||
current_synt = synthesizers_cache[synt_path]
|
||||
print("using synthesizer model: " + str(synt_path))
|
||||
# Load input wav
|
||||
if "upfile_b64" in request.form:
|
||||
wav_base64 = request.form["upfile_b64"]
|
||||
wav = base64.b64decode(bytes(wav_base64, 'utf-8'))
|
||||
wav = pcm2float(np.frombuffer(wav, dtype=np.int16), dtype=np.float32)
|
||||
sample_rate = Synthesizer.sample_rate
|
||||
else:
|
||||
wav, sample_rate, = librosa.load(request.files['file'])
|
||||
write("temp.wav", sample_rate, wav) #Make sure we get the correct wav
|
||||
|
||||
encoder_wav = encoder.preprocess_wav(wav, sample_rate)
|
||||
wav_base64 = request.form["upfile_b64"]
|
||||
wav = base64.b64decode(bytes(wav_base64, 'utf-8'))
|
||||
wav = pcm2float(np.frombuffer(wav, dtype=np.int16), dtype=np.float32)
|
||||
encoder_wav = encoder.preprocess_wav(wav, 16000)
|
||||
embed, _, _ = encoder.embed_utterance(encoder_wav, return_partials=True)
|
||||
|
||||
# Load input text
|
||||
@@ -107,7 +100,6 @@ def webApp():
|
||||
embeds = [embed] * len(texts)
|
||||
specs = current_synt.synthesize_spectrograms(texts, embeds)
|
||||
spec = np.concatenate(specs, axis=1)
|
||||
# wav = rnn_vocoder.infer_waveform(spec)
|
||||
wav = gan_vocoder.infer_waveform(spec)
|
||||
|
||||
# Return cooked wav
|
||||
|
||||
@@ -5,4 +5,3 @@ PORT = 8080
|
||||
MAX_CONTENT_PATH =1024 * 1024 * 4 # mp3文件大小限定不能超过4M
|
||||
SECRET_KEY = "mockingbird_key"
|
||||
WTF_CSRF_SECRET_KEY = "mockingbird_key"
|
||||
TEMPLATES_AUTO_RELOAD = True
|
||||
@@ -38,37 +38,22 @@
|
||||
</div>
|
||||
|
||||
<div style="margin-left: 5%;margin-top: 50px;width: 90%;">
|
||||
<div style="font-size: larger;font-weight: bolder;">1. 请输入中文</div>
|
||||
<div style="font-size: larger;font-weight: bolder;">请输入中文</div>
|
||||
<textarea id="user_input_text"
|
||||
style="border:1px solid #ccc; width: 100%; height: 100px; font-size: 15px; margin-top: 10px;"></textarea>
|
||||
</div>
|
||||
<div class="pd btns" style="margin-left: 5%;margin-top: 20px;width: 90%; ">
|
||||
|
||||
<div class="pd btns" style="margin-left: 5%;margin-top: 20px;width: 90%; text-align:right;">
|
||||
<!-- <div>
|
||||
<button onclick="recOpen()" style="margin-right:10px">打开录音,请求权限</button>
|
||||
<button onclick="recClose()" style="margin-right:0">关闭录音,释放资源</button>
|
||||
</div> -->
|
||||
<div style="font-size: larger;font-weight: bolder;">2. 请直接录音，点击停止结束</div>
|
||||
<button onclick="recStart()" >录制</button>
|
||||
<button onclick="recStop()">停止</button>
|
||||
<button onclick="recPlay()" >播放</button>
|
||||
<button onclick="recUpload()" >上传</button>
|
||||
</div>
|
||||
<div class="pd btns" style="margin-left: 5%;margin-top: 20px;width: 90%; ">
|
||||
<div style="font-size: larger;font-weight: bolder;">或上传音频</div>
|
||||
<input type="file" id="fileInput" accept=".wav" />
|
||||
<label for="fileInput">选择音频</label>
|
||||
<div id="audio1"></div>
|
||||
</div>
|
||||
<div class="pd btns" style="margin-left: 5%;margin-top: 20px;width: 90%; ">
|
||||
<div style="font-size: larger;font-weight: bolder;">3. 选择Synthesizer模型</div>
|
||||
<span class="box">
|
||||
<select id="select">
|
||||
</select>
|
||||
</span>
|
||||
</div>
|
||||
<div class="pd btns" style="margin-left: 5%;margin-top: 20px;width: 90%; text-align:right;">
|
||||
<button id="upload" onclick="recUpload()">上传合成</button>
|
||||
</div>
|
||||
|
||||
|
||||
<!-- 波形绘制区域 -->
|
||||
<!-- <div class="pd recpower">
|
||||
<div style="height:40px;width:100%;background:#fff;position:relative;">
|
||||
@@ -91,37 +76,6 @@
|
||||
|
||||
|
||||
<script>
|
||||
|
||||
$("#fileInput").change(function(){
|
||||
var file = $("#fileInput").get(0).files;
|
||||
if (file.length > 0) {
|
||||
var path = URL.createObjectURL(file[0]);
|
||||
var audio = document.createElement('audio');
|
||||
audio.src = path;
|
||||
audio.controls = true;
|
||||
$('#audio1').empty().append(audio);
|
||||
}
|
||||
});
|
||||
|
||||
fetch("/api/synthesizers", {
|
||||
method: 'get',
|
||||
headers: {
|
||||
"X-CSRFToken": "{{ csrf_token() }}"
|
||||
}
|
||||
}).then(function (res) {
|
||||
if (!res.ok) throw Error(res.statusText);
|
||||
return res.json();
|
||||
}).then(function (data) {
|
||||
for (var synt of data) {
|
||||
var option = document.createElement('option');
|
||||
option.text = synt.name
|
||||
option.value = synt.path
|
||||
$("#select").append(option);
|
||||
}
|
||||
}).catch(function (err) {
|
||||
console.log('Error: ' + err.message);
|
||||
})
|
||||
|
||||
var rec, wave, recBlob;
|
||||
/**调用open打开录音请求好录音权限**/
|
||||
var recOpen = function () {//一般在显示出录音按钮或相关的录音界面时进行此方法调用，后面用户点击开始录音时就能畅通无阻了
|
||||
@@ -240,15 +194,9 @@
|
||||
|
||||
/**上传**/
|
||||
function recUpload() {
|
||||
var blob
|
||||
var loadedAudios = $("#fileInput").get(0).files
|
||||
if (loadedAudios.length > 0) {
|
||||
blob = loadedAudios[0];
|
||||
} else {
|
||||
blob = recBlob;
|
||||
}
|
||||
var blob = recBlob;
|
||||
if (!blob) {
|
||||
reclog("请先录音或选择音频，然后停止后再上传", 1);
|
||||
reclog("请先录音，然后停止后再上传", 1);
|
||||
return;
|
||||
};
|
||||
|
||||
@@ -263,18 +211,15 @@
|
||||
var csrftoken = "{{ csrf_token() }}";
|
||||
var user_input_text = document.getElementById("user_input_text");
|
||||
var input_text = user_input_text.value;
|
||||
var postData = new FormData();
|
||||
postData.append("text", input_text)
|
||||
postData.append("file", blob)
|
||||
var sel = document.getElementById("select");
|
||||
var path = sel.options[sel.selectedIndex].value;
|
||||
if (!!path) {
|
||||
postData.append("synt_path", path);
|
||||
}
|
||||
var postData = "";
|
||||
postData += "mime=" + encodeURIComponent(blob.type);//告诉后端，这个录音是什么格式的，可能前后端都固定的mp3可以不用写
|
||||
postData += "&upfile_b64=" + encodeURIComponent((/.+;\s*base64\s*,\s*(.+)$/i.exec(reader.result) || [])[1]) //录音文件内容，后端进行base64解码成二进制
|
||||
postData += "&text=" + encodeURIComponent(input_text);
|
||||
|
||||
fetch(api, {
|
||||
method: 'post',
|
||||
headers: {
|
||||
"Content-type": "application/x-www-form-urlencoded; charset=UTF-8",
|
||||
"X-CSRFToken": csrftoken
|
||||
},
|
||||
body: postData
|
||||
@@ -393,6 +338,7 @@
|
||||
padding: 12px;
|
||||
border-radius: 6px;
|
||||
background: #fff;
|
||||
--border: 1px solid #327de8;
|
||||
box-shadow: 2px 2px 3px #aaa;
|
||||
}
|
||||
|
||||
@@ -402,7 +348,7 @@
|
||||
cursor: pointer;
|
||||
border: none;
|
||||
border-radius: 3px;
|
||||
background: #5698c3;
|
||||
background: #327de8;
|
||||
color: #fff;
|
||||
padding: 0 15px;
|
||||
margin: 3px 10px 3px 0;
|
||||
@@ -413,13 +359,6 @@
|
||||
vertical-align: middle;
|
||||
}
|
||||
|
||||
.btns #upload {
|
||||
background: #5698c3;
|
||||
color: #fff;
|
||||
width: 100px;
|
||||
height: 42px;
|
||||
}
|
||||
|
||||
.btns button:active {
|
||||
background: #5da1f5
|
||||
}
|
||||
@@ -440,68 +379,6 @@
|
||||
padding: 2px 8px;
|
||||
border-radius: 99px;
|
||||
}
|
||||
|
||||
#fileInput {
|
||||
width: 0.1px;
|
||||
height: 0.1px;
|
||||
opacity: 0;
|
||||
overflow: hidden;
|
||||
position: absolute;
|
||||
z-index: -1;
|
||||
}
|
||||
#fileInput + label {
|
||||
padding: 0 15px;
|
||||
border-radius: 4px;
|
||||
color: white;
|
||||
background-color: #5698c3;
|
||||
display: inline-block;
|
||||
width: 70px;
|
||||
line-height: 36px;
|
||||
height: 36px;
|
||||
}
|
||||
#fileInput + label {
|
||||
cursor: pointer; /* "hand" cursor */
|
||||
}
|
||||
#fileInput:focus + label,
|
||||
#fileInput + label:hover {
|
||||
background-color: #5da1f5;
|
||||
}
|
||||
|
||||
.box select {
|
||||
background-color: #5698c3;
|
||||
color: white;
|
||||
padding: 8px;
|
||||
width: 120px;
|
||||
border: none;
|
||||
border-radius: 4px;
|
||||
font-size: 0.5em;
|
||||
outline: none;
|
||||
margin: 3px 10px 3px 0;
|
||||
}
|
||||
|
||||
.box::before {
|
||||
content: "\f13a";
|
||||
position: absolute;
|
||||
top: 0;
|
||||
right: 0;
|
||||
width: 20%;
|
||||
height: 100%;
|
||||
text-align: center;
|
||||
font-size: 28px;
|
||||
line-height: 45px;
|
||||
color: rgba(255, 255, 255, 0.5);
|
||||
background-color: rgba(255, 255, 255, 0.1);
|
||||
pointer-events: none;
|
||||
}
|
||||
|
||||
.box:hover::before {
|
||||
color: rgba(255, 255, 255, 0.6);
|
||||
background-color: rgba(255, 255, 255, 0.2);
|
||||
}
|
||||
|
||||
.box select option {
|
||||
padding: 30px;
|
||||
}
|
||||
</style>
|
||||
|
||||
</body>
|
||||
|
||||
Reference in New Issue
Block a user