-
### Describe the bug
What should we do for text that contains multiple languages? Since inference sends everything to eSpeak with a fixed language setting, eSpeak does not handle it well!
### To Rep…
-
I try both python 3.10 and 3.11
```
PS D:\AI\Bot\VITS_TXT_to_Audio> pip install -r .\requirements.txt
Looking in indexes: https://mirrors.aliyun.com/pypi/simple
Collecting pyopenjtalk
Using c…
-
GPT-SoVITS 语音总是使用的默认的模型
验证模型：
GPT-SoVITS-v2-240821>runtime\python.exe webui.py zh_CN 语音推理正常
Number of parameter: 77.61M
Number of parameter: 77.61M
实际输入的参考文本: 你好我是娜酱，来自绝区零，是一个游戏角色，欢迎来到未来世界。
…
-
### Describe the bug
```
Traceback (most recent call last):
File "/Users/hiwanz/.pyenv/versions/3.10.11/bin/svc-gui", line 8, in
sys.exit(main())
File "/Users/hiwanz/.pyenv/versions/3.…
-
i needed to change the default file to this to make this work
> numpy
flask
flask-cloudflared
flask-cors
flask-compress
markdown
Pillow
colorama
webuiapi
--extra-index-url https://download.p…
-
**🚀 Feature Description**
I tried **fine-tuning** a model(**vits**) and found that the resulting model size was too large (800+ MB, model type: vits), but the model downloaded from hugging Face w…
-
感谢您分享这个优秀的项目
我看v2支持了无文本参考的模式，但是看代码vits只有在推理阶段通过test参数控制是否输入text，如果只在推理阶段将vits中的text置0的话测下来会出现**部分语音咬字的音调或者清音错误**，请问v2还有其他操作避免这个问题吗？
-
Thanks for the great work!
There's one thing that confuses me very much though. In the paper, the KL loss is computed as (Eq.3) .
In vanilla VAEs, the KL loss is actually an **expectation**. As the…
-
### Proposal Summary
I would want [to_patches()](https://voxel51.com/docs/fiftyone/user_guide/app.html#viewing-object-patches) to be as though I am seeing a bunch of crops of the image and it's met…
-
I was looking ove rthe implementation of you text to speech model. Is it working fine and if it is working then from where can I test It.
Thanks in advance.