-
from pathlib import Path
import soundfile as sf
import os
from paddlespeech.t2s.exps.syn_utils import get_am_output
from paddlespeech.t2s.exps.syn_utils import get_frontend
from paddlespeech.t2…
-
请问如何对多个数据集进行合并,并进行训练以降低Loss?
我已经下载了三个数据集
├──aidatatang_200zh
│ ├──corpus
│ │ ├──dev
│ │ ├──test
│ │ └──train
│ └──transcript
├──data_aishell3
│ ├──test
│ │ └──wav
│ └──train
…
-
我使用了paddle官网教程(https://aistudio.baidu.com/aistudio/projectdetail/6572581)的代码:
import paddle
import yaml
import soundfile as sf
from yacs.config import CfgNode
from paddlespeech.t2s.frontend.mix_f…
-
您好感谢你们公开的工作,不过有个问题想请教下。我在尝试examples/aishell3/vc2 TCAPA-TDNN的voice clone时,我直接跑了run.sh中voice_clone这部。我使用的测试src是我自己的原声(男声),但是tts出来的结果竟然是女声。我使用的都是预训练模型。请问这是不是spk_embedding有问题也就是tcapa-tdnn提取的有问题。
-
The next generation Kaldi is developing rapidly. We have gotten some competitive results in some large and popular datasets based on k2, icefall, and Lhotse. Now, we want to apply it to many datasets.…
-
Aishell3 vc2 example not using 16k sample rate while extracting spk embedding
Although it checks the sample rate of input audio but I don't see any process that handles the resampling work.
https:…
-
请问一下,微调时大概训练多久。我在自己训练的模型尝试加入反向kl loss微调,反而kl loss 变大,生成效果很差
-
1. [transformer tts](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/examples/ljspeech/tts1)
2. 使用paddle2.4.2+(develop or r1.4.1),进行transformer tts预训练模型推理的结果语音正常
3. 使用paddle2.5.1+(develop…
-
D:\迅雷下载\MockingBird-main>python demo_toolbox.py
Arguments:
datasets_root: None
enc_models_dir: encoder\saved_models
syn_models_dir: synthesizer\saved_models
voc_models_dir:…
-
按照文档,在conda虚拟环境先安装了paddle-gpu版本,再安装了paddlespeech。调用PaddleSpeech/examples/aishell3/vits/local/preprocess.sh预处理shell处理数据时,报错。根据报错应该是paddle的numpy和paddlespeech需要的版本不一致,我也不敢贸然修改numpy的版本,因为可能导致paddle出什么问题。有…