-
**Summary[问题简述(一句话)]**
我在实验室的机器上训练,使用的是我自己收集的,并且用aishell3数据集格式标注的数据,总是报这个错误(见截图)
**Env & To Reproduce[复现与环境]**
OS: CentOS 7
Python: Anaconda+python 3.8
pytorch:1.11.0
CUDA:11.4
**Screenshots[…
-
Hi!
I used jets to run on the aishell3 dataset, but the text information was not aligned(the synthesized speech has no semantic information).
I have tried other models (such as joint fs2 hifigan, ta…
-
i want to generate duration when executing [https://github.com/espnet/espnet/blob/master/egs2/aishell3/tts1/local/data.sh](url)
at stege 1, the shell executes [https://github.com/espnet/espnet/blob/m…
-
Thanks for your excellent work and opening source! I have a few questions as follows:
1. Since it may take days or weeks to pre-train it again. Can you provide the pre-trained tts model checkpoint? I…
-
现在使用aishell3数据集训练了100k左右,推理出来只有“得得得得”这种的合成声音.
我看相较于https://github.com/jaywalnut310/vits版本参数多了一个bert,我试着修改了下,数据集上加上了speaker
是否还需要修改什么.
![image](https://user-images.githubusercontent.com/17938613/225…
-
I wanted to test the paddlespeech repo to clone a voice . My target text is english. (is that possible?)
Here are the steps that ive taken.
- cloned the repo (` /mnt/msd/users/arnav/ ` is my works…
-
Hi,
I have trained a good fs2 model based on aishell3, and I want to train a bilingual model, so I add VCTK corpus, use G2p_en to convert word to phoneme. I get a mix phoneme token list from mix text…
-
## General Question
Speech Server一键部署语音服务,使用am为fastspeech2_aishell3,voc为pwgan_aishell3,生成的短句音频句首第一个字和句末最后一个字有吞音,句末吞音现象尤其严重,不加标点的话几乎听不到最后一个字。
-
@Plachtaa 大哥,有好用的中文底模了么?目前的C模型效果不太行
-
在文档中https://paddlespeech.readthedocs.io/en/latest/tts/demo.html#style-control-in-fastspeech2 我看是支持语速的微调
demo使用的例子是 demos/style_fs2/style_syn.py
- 使用的模型是fastspeech2_csmsc-zh
理论上讲只要是FastSpeec…