GPT-SoVITS
GPT-SoVITS copied to clipboard
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
- **uvr5,语音切分和ASR默认输出目录是output下对应的文件夹,但是当训练不同模型时,文件夹内的文件就会变得冗杂。我建议在根目录下新建一个Dataset文件夹,在其中新建相关子文件夹(如下图)**。  - **其中ProjectName文件夹及其子文件夹通过webui统一生成**。  - **在webui里面输入对应数据集名称,如果没有对应文件夹,则会生成文件夹。后续输出目录都变成ProjectName/xxx(如果已经存在也设置为ProjectName/xxx),这样在数据集分类方面会很方便。** 以下为部分代码(编程基础不好,只写了部分) 
代码中好像只有one shot的train和inference,怎么进行zero shot ?
I downloaded the zip and ran the go-webui.bat Here's what came up in the terminal ``` Fatal Python error: init_import_site: Failed to import the site module Python runtime state: initialized...
IndexError: list index out of range DEBUG:httpx._client:HTTP Request: POST http://localhost:9872/api/predict "HTTP/1.1 500 Internal Server Error" DEBUG:httpx._client:HTTP Request: POST http://localhost:9872/reset "HTTP/1.1 200 OK" Traceback (most recent call last): File "F:\GPT-SoVITS\runtime\lib\site-packages\gradio\routes.py", line...
Traceback (most recent call last): File "/ML-A100/team/mm/chen/GPT-SoVITS/GPT_SoVITS/inference_webui.py", line 28, in from text.cleaner import clean_text File "/ML-A100/team/mm/chen/GPT-SoVITS/GPT_SoVITS/text/cleaner.py", line 1, in from text import chinese, japanese, cleaned_text_to_sequence, symbols, english File "/ML-A100/team/mm/chen/GPT-SoVITS/GPT_SoVITS/text/japanese.py", line...
change the modelscope pipeline to funasr1.0
```javascript During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/root/app/GPT-SoVITS/webui.py", line 744, in app.queue(concurrency_count=511, max_size=1022).launch( File "/root/miniconda3/envs/GPTSoVits/lib/python3.9/site-packages/gradio/blocks.py", line 1347, in launch server_name, server_port,...