pflowtts_pytorch下载pflowtts_pytorch源代码下载

论文p-flow的非官方实施：通过NVIDIA的语音提示，快速且具有数据效率的零击中。

尽管最近大规模的神经编解码器语言模型通过对数千个小时的数据进行培训显示了零拍的零TTS的显着改善，但它们遭受了缺点，例如缺乏稳健性，与以前的自动回应TTS方法相似的缓慢采样速度以及对预先培训的神经编解码器表示的依赖。我们的工作提出了P-Flow，这是一种快速且数据效率高的零摄像TTS模型，该模型使用语音提示进行演讲者的适应性。 p-flow包含用于扬声器适应的语音提示的文本编码器，以及用于高质量和快速语音综合的流量匹配生成解码器。我们的语音启示文本编码器使用语音提示和文本输入来生成扬声器条件文本表示。流量匹配的生成解码器使用扬声器条件输出来综合高质量的个性化语音，明显快得多。与神经编解码器的语言模型不同，我们使用连续的MEL代理在Libritts数据集上专门训练P-Flow。通过我们使用连续语音提示的训练方法，p-flow匹配了大规模零击中TTS模型的扬声器相似性性能，其训练数据较少，并且具有超过20倍的训练速度。我们的结果表明，p-flow具有更好的发音，并且在人类的相似性和说话者的相似性中被优先于其最近的最新对应物，从而将p-flow定义为一种有吸引力且值得期望的替代方案。

 cd pflowtts_pytorch/notebooks

 import sys
sys . path . append ( '..' )

from pflow . models . pflow_tts import pflowTTS
import torch
from dataclasses import dataclass

@ dataclass
class DurationPredictorParams :
    filter_channels_dp : int
    kernel_size : int
    p_dropout : float

@ dataclass
class EncoderParams :
    n_feats : int
    n_channels : int
    filter_channels : int
    filter_channels_dp : int
    n_heads : int
    n_layers : int
    kernel_size : int
    p_dropout : float
    spk_emb_dim : int
    n_spks : int
    prenet : bool

@ dataclass
class CFMParams :
    name : str
    solver : str
    sigma_min : float

# Example usage
duration_predictor_params = DurationPredictorParams (
    filter_channels_dp = 256 ,
    kernel_size = 3 ,
    p_dropout = 0.1
)

encoder_params = EncoderParams (
    n_feats = 80 ,
    n_channels = 192 ,
    filter_channels = 768 ,
    filter_channels_dp = 256 ,
    n_heads = 2 ,
    n_layers = 6 ,
    kernel_size = 3 ,
    p_dropout = 0.1 ,
    spk_emb_dim = 64 ,
    n_spks = 1 ,
    prenet = True
)

cfm_params = CFMParams (
    name = 'CFM' ,
    solver = 'euler' ,
    sigma_min = 1e-4
)

@ dataclass
class EncoderOverallParams :
    encoder_type : str
    encoder_params : EncoderParams
    duration_predictor_params : DurationPredictorParams

encoder_overall_params = EncoderOverallParams (
    encoder_type = 'RoPE Encoder' ,
    encoder_params = encoder_params ,
    duration_predictor_params = duration_predictor_params
)

@ dataclass
class DecoderParams :
    channels : tuple
    dropout : float
    attention_head_dim : int
    n_blocks : int
    num_mid_blocks : int
    num_heads : int
    act_fn : str

decoder_params = DecoderParams (
    channels = ( 256 , 256 ),
    dropout = 0.05 ,
    attention_head_dim = 64 ,
    n_blocks = 1 ,
    num_mid_blocks = 2 ,
    num_heads = 2 ,
    act_fn = 'snakebeta' ,
)
    
model = pflowTTS (
    n_vocab = 100 ,
    n_feats = 80 ,
    encoder = encoder_overall_params ,
    decoder = decoder_params . __dict__ ,
    cfm = cfm_params ,
    data_statistics = None ,
)

x = torch . randint ( 0 , 100 , ( 4 , 20 ))
x_lengths = torch . randint ( 10 , 20 , ( 4 ,))
y = torch . randn ( 4 , 80 , 500 )
y_lengths = torch . randint ( 300 , 500 , ( 4 ,))

dur_loss , prior_loss , diff_loss , attn = model ( x , x_lengths , y , y_lengths )
# backpropagate the loss 

# now synthesises
x = torch . randint ( 0 , 100 , ( 1 , 20 ))
x_lengths = torch . randint ( 10 , 20 , ( 1 ,))
y_slice = torch . randn ( 1 , 80 , 264 )

model . synthesise ( x , x_lengths , y_slice , n_timesteps = 10 )

conda create -n pflowtts python=3.10 -y
conda activate pflowtts

 cd pflowtts_pytorch
pip install -r requirements.txt

 # Cython-version Monotonoic Alignment Search
python setup.py build_ext --inplace

 train_filelist_path : data/filelists/ljs_audio_text_train_filelist.txt
valid_filelist_path : data/filelists/ljs_audio_text_val_filelist.txt

 ! mkdir -p /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists
! wget -O /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists/ljs_audio_text_test_filelist.txt https://raw.githubusercontent.com/NVIDIA/tacotron2/master/filelists/ljs_audio_text_test_filelist.txt
! wget -O /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists/ljs_audio_text_train_filelist.txt https://raw.githubusercontent.com/NVIDIA/tacotron2/master/filelists/ljs_audio_text_train_filelist.txt
! wget -O /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists/ljs_audio_text_val_filelist.txt https://raw.githubusercontent.com/NVIDIA/tacotron2/master/filelists/ljs_audio_text_val_filelist.txt

! sed -i -- ' s,DUMMY,/home/ubuntu/LJSpeech/LJSpeech-1.1/wavs,g ' /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists/ * .txt

! sed -i -- ' s,train_filelist_path: data/filelists/ljs_audio_text_train_filelist.txt,train_filelist_path: /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists/ljs_audio_text_train_filelist.txt,g ' /home/ubuntu/LJSpeech/pflowtts_pytorch/configs/data/ljspeech.yaml
! sed -i -- ' s,valid_filelist_path: data/filelists/ljs_audio_text_val_filelist.txt,valid_filelist_path: /home/ubuntu/LJSpeech/LJSpeech-1.1/filelists/ljs_audio_text_val_filelist.txt,g ' /home/ubuntu/LJSpeech/pflowtts_pytorch/configs/data/ljspeech.yaml

 cd pflowtts_pytorch/pflow/utils
python generate_data_statistics.py -i ljspeech.yaml
# Output:
#{ ' mel_mean ' : -5.53662231756592, ' mel_std ' : 2.1161014277038574}

在data_statistics密钥下，在configs/data/ljspeech.yaml中更新这些值。